{"id":46,"date":"2017-02-02T19:11:05","date_gmt":"2017-02-02T19:11:05","guid":{"rendered":"http:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/wordpress\/?page_id=46"},"modified":"2017-02-02T19:11:05","modified_gmt":"2017-02-02T19:11:05","slug":"publications","status":"publish","type":"page","link":"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/homepage\/?page_id=46","title":{"rendered":"Publications"},"content":{"rendered":"<h2>Conference and journal papers<\/h2>\n<div class=\"teachpress_pub_list\"><form name=\"tppublistform\" method=\"get\"><a name=\"tppubs\" id=\"tppubs\"><\/a><\/form><div class=\"teachpress_publication_list\"><h3 class=\"tp_h3\" id=\"tp_h3_2026\">2026<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Macfarlane, M.;  Bonnet, C.; van Hoof, H.;  Lelis, L.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('227','tp_links')\" style=\"cursor:pointer;\">Gradient-Based Program Synthesis with Neurally Interpreted Languages<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <span class=\"tp_pub_label_status forthcoming\">Forthcoming<\/span><\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Conference on Learning Representations, <\/span>Forthcoming.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_227\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('227','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_227\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('227','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_227\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{macfarlane2026gradient,<br \/>\r\ntitle = {Gradient-Based Program Synthesis with Neurally Interpreted Languages},<br \/>\r\nauthor = {Macfarlane, M. and Bonnet, C. and van Hoof, H. and Lelis, L.},<br \/>\r\nurl = {https:\/\/openreview.net\/forum?id=NAORIWBaoO},<br \/>\r\nyear  = {2026},<br \/>\r\ndate = {2026-04-23},<br \/>\r\nbooktitle = {Proceedings of the International Conference on Learning Representations},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {forthcoming},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('227','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_227\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/openreview.net\/forum?id=NAORIWBaoO\" title=\"https:\/\/openreview.net\/forum?id=NAORIWBaoO\" target=\"_blank\">https:\/\/openreview.net\/forum?id=NAORIWBaoO<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('227','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2025\">2025<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoepner, Niklas;  Kuric, David; van Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('225','tp_links')\" style=\"cursor:pointer;\">Making Universal Policies Universal<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, <\/span><span class=\"tp_pub_additional_pages\">pp. 2553\u20132555, <\/span><span class=\"tp_pub_additional_year\">2025<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_225\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('225','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_225\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('225','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_225\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{hoepner2025making,<br \/>\r\ntitle = {Making Universal Policies Universal},<br \/>\r\nauthor = {Hoepner, Niklas and Kuric, David and van Hoof, Herke},<br \/>\r\nurl = {https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3709347.3743934<br \/>\r\nhttps:\/\/arxiv.org\/abs\/2502.14777},<br \/>\r\nyear  = {2025},<br \/>\r\ndate = {2025-05-21},<br \/>\r\nbooktitle = {Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems},<br \/>\r\npages = {2553\u20132555},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('225','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_225\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3709347.3743934\" title=\"https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3709347.3743934\" target=\"_blank\">https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3709347.3743934<\/a><\/li><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2502.14777\" title=\"https:\/\/arxiv.org\/abs\/2502.14777\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2502.14777<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('225','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoepner, Niklas;  Tiddi, Ilaria; van Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('226','tp_links')\" style=\"cursor:pointer;\">Data Augmentation for Instruction Following Policies via Trajectory Segmentation<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the AAAI Conference on Artificial Intelligence, <\/span><span class=\"tp_pub_additional_pages\">pp. 17214-17222, <\/span><span class=\"tp_pub_additional_year\">2025<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_226\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('226','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_226\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('226','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_226\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{hoepner2025data,<br \/>\r\ntitle = {Data Augmentation for Instruction Following Policies via Trajectory Segmentation},<br \/>\r\nauthor = {Hoepner, Niklas and Tiddi, Ilaria and van Hoof, Herke},<br \/>\r\nurl = {https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/33892<br \/>\r\nhttps:\/\/arxiv.org\/abs\/2503.01871},<br \/>\r\nyear  = {2025},<br \/>\r\ndate = {2025-04-01},<br \/>\r\nurldate = {2025-04-01},<br \/>\r\nbooktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},<br \/>\r\nvolume = {39},<br \/>\r\nnumber = {16},<br \/>\r\npages = {17214-17222},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('226','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_226\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/33892\" title=\"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/33892\" target=\"_blank\">https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/33892<\/a><\/li><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2503.01871\" title=\"https:\/\/arxiv.org\/abs\/2503.01871\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2503.01871<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('226','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2024\">2024<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Mansoury, Masoud;  Mobasher, Bamshad; van Hoof, Herke<\/p><p class=\"tp_pub_title\">Mitigating Exposure Bias in Online Learning to Rank Recommendation: A Novel Reward Model for Cascading Bandits <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">ACM International Conference on Information and Knowledge Management, <\/span><span class=\"tp_pub_additional_year\">2024<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_224\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('224','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_224\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{mansoury2024mitigating,<br \/>\r\ntitle = {Mitigating Exposure Bias in Online Learning to Rank Recommendation: A Novel Reward Model for Cascading Bandits},<br \/>\r\nauthor = {Masoud Mansoury and Bamshad Mobasher and van Hoof, Herke<br \/>\r\n},<br \/>\r\nyear  = {2024},<br \/>\r\ndate = {2024-10-21},<br \/>\r\nurldate = {2024-10-21},<br \/>\r\nbooktitle = {ACM International Conference on Information and Knowledge Management},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('224','tp_bibtex')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Giri, Charul;  Granmo, Ole Christoffer; van Hoof, Herke<\/p><p class=\"tp_pub_title\">Accelerated Tsetlin Machine Inference Through Incremental Model Re-evaluation <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Symposium on Tsetlin Machines, <\/span><span class=\"tp_pub_additional_year\">2024<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_223\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('223','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_223\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{giri2024accelerated,<br \/>\r\ntitle = {Accelerated Tsetlin Machine Inference Through Incremental Model Re-evaluation},<br \/>\r\nauthor = {Charul Giri and Ole Christoffer Granmo and Herke van Hoof},<br \/>\r\nyear  = {2024},<br \/>\r\ndate = {2024-08-29},<br \/>\r\nurldate = {2024-08-29},<br \/>\r\nbooktitle = {International Symposium on Tsetlin Machines},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('223','tp_bibtex')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Huang, Jin;  Oosterhuis, Harrie;  Mansoury, Masoud; van Hoof, Herke; de Rijke, Maarten<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('221','tp_links')\" style=\"cursor:pointer;\">Going Beyond Popularity and Positivity Bias: Correcting for Multifactorial Bias in Recommender Systems<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International ACM SIGIR Conference on Research and Development in Information Retrieval, <\/span><span class=\"tp_pub_additional_year\">2024<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_221\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('221','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_221\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('221','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_221\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{huang2024going,<br \/>\r\ntitle = {Going Beyond Popularity and Positivity Bias: Correcting for Multifactorial Bias in Recommender Systems},<br \/>\r\nauthor = {Huang, Jin and Oosterhuis, Harrie and Mansoury, Masoud and van Hoof, Herke and de Rijke, Maarten},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2404.18640},<br \/>\r\nyear  = {2024},<br \/>\r\ndate = {2024-07-14},<br \/>\r\nurldate = {2024-07-14},<br \/>\r\nbooktitle = {International ACM SIGIR Conference on Research and Development in Information Retrieval},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('221','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_221\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2404.18640\" title=\"https:\/\/arxiv.org\/abs\/2404.18640\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2404.18640<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('221','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Kuric, D.;  Infante, G.;  G\u00f3mez, V.;  Jonsson, A.; van Hoof, H.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('220','tp_links')\" style=\"cursor:pointer;\">Planning with a Learned Policy Basis to Optimally Solve Complex Tasks<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Automated Planning and Scheduling, <\/span><span class=\"tp_pub_additional_year\">2024<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_220\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('220','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_220\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('220','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_220\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{kuric2024planning,<br \/>\r\ntitle = {Planning with a Learned Policy Basis to Optimally Solve Complex Tasks},<br \/>\r\nauthor = {Kuric, D. and Infante, G. and G\u00f3mez, V. and Jonsson, A. and van Hoof, H. },<br \/>\r\nurl = {https:\/\/openreview.net\/forum?id=6N1uCtBhcL},<br \/>\r\nyear  = {2024},<br \/>\r\ndate = {2024-06-01},<br \/>\r\nurldate = {2024-06-01},<br \/>\r\nbooktitle = {International Conference on Automated Planning and Scheduling},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('220','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_220\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/openreview.net\/forum?id=6N1uCtBhcL\" title=\"https:\/\/openreview.net\/forum?id=6N1uCtBhcL\" target=\"_blank\">https:\/\/openreview.net\/forum?id=6N1uCtBhcL<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('220','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Loftin, Robert;  \u00c7elikok, Mustafa Mert; van Hoof, Herke;  Kaski, Samuel;  Oliehoek, Frans<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('219','tp_links')\" style=\"cursor:pointer;\">Uncoupled Learning of Differential Stackelberg Equilibria with Commitments<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Artificial Agents and Multi-Agent Systems (AAMAS), <\/span><span class=\"tp_pub_additional_year\">2024<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_219\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('219','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_219\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('219','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_219\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{loftin2024uncoupled,<br \/>\r\ntitle = {Uncoupled Learning of Differential Stackelberg Equilibria with Commitments},<br \/>\r\nauthor = {Loftin, Robert and \u00c7elikok, Mustafa Mert and van Hoof, Herke and Kaski, Samuel and Oliehoek, Frans},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2302.03438},<br \/>\r\nyear  = {2024},<br \/>\r\ndate = {2024-05-06},<br \/>\r\nurldate = {2024-05-06},<br \/>\r\nbooktitle = {Artificial Agents and Multi-Agent Systems (AAMAS)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('219','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_219\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2302.03438\" title=\"https:\/\/arxiv.org\/abs\/2302.03438\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2302.03438<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('219','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2023\">2023<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Woehlke, J.;  Schmitt, F.; van Hoof, H.<\/p><p class=\"tp_pub_title\">Learning Hierarchical Planning-Based Policies from Offline Data <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Machine Learning and Knowledge Discovery in Databases: Research Track (ECML PKDD), <\/span><span class=\"tp_pub_additional_year\">2023<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_218\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('218','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_218\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{learning2023woehlke,<br \/>\r\ntitle = {Learning Hierarchical Planning-Based Policies from Offline Data},<br \/>\r\nauthor = {Woehlke, J. and Schmitt, F. and van Hoof, H. },<br \/>\r\nyear  = {2023},<br \/>\r\ndate = {2023-09-18},<br \/>\r\nbooktitle = {Machine Learning and Knowledge Discovery in Databases: Research Track (ECML PKDD)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('218','tp_bibtex')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Bakker, T.; van Hoof, H.;  Welling, M.<\/p><p class=\"tp_pub_title\"> Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Machine Learning and Knowledge Discovery in Databases: Research Track (ECML PKDD), <\/span><span class=\"tp_pub_additional_year\">2023<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_217\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('217','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_217\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{bakker2023learning,<br \/>\r\ntitle = { Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes},<br \/>\r\nauthor = {Bakker, T. and van Hoof, H. and Welling, M. },<br \/>\r\nyear  = {2023},<br \/>\r\ndate = {2023-09-17},<br \/>\r\nurldate = {2023-09-17},<br \/>\r\nbooktitle = {Machine Learning and Knowledge Discovery in Databases: Research Track (ECML PKDD)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('217','tp_bibtex')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Wang, Qi;  Federici, Marco;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('213','tp_links')\" style=\"cursor:pointer;\">Bridge the Inference Gaps of Neural Processes via Expectation Maximization<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Learning Representations, <\/span><span class=\"tp_pub_additional_year\">2023<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_213\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('213','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_213\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('213','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_213\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{wang2023bridge,<br \/>\r\ntitle = {Bridge the Inference Gaps of Neural Processes via Expectation Maximization},<br \/>\r\nauthor = {Qi Wang and Marco Federici and Herke Hoof},<br \/>\r\nurl = {https:\/\/openreview.net\/forum?id=A7v2DqLjZdq},<br \/>\r\nyear  = {2023},<br \/>\r\ndate = {2023-05-01},<br \/>\r\nurldate = {2023-05-01},<br \/>\r\nbooktitle = {International Conference on Learning Representations},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('213','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_213\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/openreview.net\/forum?id=A7v2DqLjZdq\" title=\"https:\/\/openreview.net\/forum?id=A7v2DqLjZdq\" target=\"_blank\">https:\/\/openreview.net\/forum?id=A7v2DqLjZdq<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('213','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_article\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Kuric, David;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('163','tp_links')\" style=\"cursor:pointer;\">Reusable Options through Gradient-based Meta Learning<\/a> <span class=\"tp_pub_type article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">Transactions on Machine Learning Research, <\/span><span class=\"tp_pub_additional_volume\">vol. 03\/2023, <\/span><span class=\"tp_pub_additional_year\">2023<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_163\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('163','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_163\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('163','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_163\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{kuric2023reusable,<br \/>\r\ntitle = {Reusable Options through Gradient-based Meta Learning},<br \/>\r\nauthor = {David Kuric and Herke Hoof},<br \/>\r\nurl = {https:\/\/openreview.net\/forum?id=qdDmxzGuzu},<br \/>\r\nyear  = {2023},<br \/>\r\ndate = {2023-03-28},<br \/>\r\nurldate = {2023-03-28},<br \/>\r\njournal = {Transactions on Machine Learning Research},<br \/>\r\nvolume = {03\/2023},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('163','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_163\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/openreview.net\/forum?id=qdDmxzGuzu\" title=\"https:\/\/openreview.net\/forum?id=qdDmxzGuzu\" target=\"_blank\">https:\/\/openreview.net\/forum?id=qdDmxzGuzu<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('163','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2022\">2022<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Wang, Qi;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('161','tp_links')\" style=\"cursor:pointer;\">Learning Expressive Meta-Representations with Mixture of Expert Neural Processes<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Advances in Neural Information Processing Systems, <\/span><span class=\"tp_pub_additional_year\">2022<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_161\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('161','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_161\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('161','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_161\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{wang2022learning,<br \/>\r\ntitle = {Learning Expressive Meta-Representations with Mixture of Expert Neural Processes},<br \/>\r\nauthor = {Qi Wang and Herke Hoof},<br \/>\r\nurl = {https:\/\/openreview.net\/forum?id=ju38DG3sbg6},<br \/>\r\nyear  = {2022},<br \/>\r\ndate = {2022-11-29},<br \/>\r\nbooktitle = {Advances in Neural Information Processing Systems},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('161','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_161\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/openreview.net\/forum?id=ju38DG3sbg6\" title=\"https:\/\/openreview.net\/forum?id=ju38DG3sbg6\" target=\"_blank\">https:\/\/openreview.net\/forum?id=ju38DG3sbg6<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('161','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Gagrani, Mukul;  Rainone, Corrado;  Yang, Yang;  Teague, Harris;  Jeon, Wonseok;  Hoof, Herke;  Zeng, Weiliang Will;  Zappi, Piero;  Lott, Christopher;  Bondesan, Roberto<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('162','tp_links')\" style=\"cursor:pointer;\">Neural Topological Ordering for Computation Graphs<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Advances in Neural Information Processing Systems, <\/span><span class=\"tp_pub_additional_year\">2022<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_162\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('162','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_162\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('162','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_162\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{gagrani2022neural,<br \/>\r\ntitle = {Neural Topological Ordering for Computation Graphs},<br \/>\r\nauthor = {Mukul Gagrani and Corrado Rainone and Yang Yang and Harris Teague and Wonseok Jeon and Herke Hoof and Weiliang Will Zeng and Piero Zappi and Christopher Lott and Roberto Bondesan},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2207.05899},<br \/>\r\nyear  = {2022},<br \/>\r\ndate = {2022-11-29},<br \/>\r\nbooktitle = {Advances in Neural Information Processing Systems},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('162','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_162\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2207.05899\" title=\"https:\/\/arxiv.org\/abs\/2207.05899\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2207.05899<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('162','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> W\u00f6hlke, Jan;  Schmitt, Felix;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('214','tp_links')\" style=\"cursor:pointer;\">Value Refinement Network (VRN)<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Joint Conference on Artificial Intelligence, <\/span><span class=\"tp_pub_additional_year\">2022<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_214\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('214','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_214\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('214','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_214\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{wohlke2022value,<br \/>\r\ntitle = {Value Refinement Network (VRN)},<br \/>\r\nauthor = {Jan W\u00f6hlke and Felix Schmitt and Herke Hoof},<br \/>\r\nurl = {https:\/\/www.ijcai.org\/proceedings\/2022\/494},<br \/>\r\nyear  = {2022},<br \/>\r\ndate = {2022-07-23},<br \/>\r\nbooktitle = {International Joint Conference on Artificial Intelligence},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('214','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_214\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/www.ijcai.org\/proceedings\/2022\/494\" title=\"https:\/\/www.ijcai.org\/proceedings\/2022\/494\" target=\"_blank\">https:\/\/www.ijcai.org\/proceedings\/2022\/494<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('214','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> H\u00f6pner, Niklas;  Tiddi, Ilaria;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('215','tp_links')\" style=\"cursor:pointer;\">Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Joint Conference on Artificial Intelligence, <\/span><span class=\"tp_pub_additional_year\">2022<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_215\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('215','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_215\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('215','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_215\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{hopner2022leveraging,<br \/>\r\ntitle = {Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods},<br \/>\r\nauthor = {Niklas H\u00f6pner and Ilaria Tiddi and Herke Hoof},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2201.12126},<br \/>\r\nyear  = {2022},<br \/>\r\ndate = {2022-07-23},<br \/>\r\nurldate = {2022-07-23},<br \/>\r\nbooktitle = {International Joint Conference on Artificial Intelligence},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('215','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_215\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2201.12126\" title=\"https:\/\/arxiv.org\/abs\/2201.12126\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2201.12126<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('215','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Giri, Charul;  Granmo, Ole-Christopher;  Hoof, Herke;  Blakely, Christian D.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('206','tp_links')\" style=\"cursor:pointer;\">Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Joint Conference on Neural Networks, <\/span><span class=\"tp_pub_additional_year\">2022<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_206\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('206','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_206\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('206','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_206\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{giri2022logic,<br \/>\r\ntitle = {Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine},<br \/>\r\nauthor = {Charul Giri and Ole-Christopher Granmo and Herke Hoof and Christian D. Blakely},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2203.04378},<br \/>\r\nyear  = {2022},<br \/>\r\ndate = {2022-07-18},<br \/>\r\nbooktitle = {International Joint Conference on Neural Networks},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('206','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_206\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2203.04378\" title=\"https:\/\/arxiv.org\/abs\/2203.04378\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2203.04378<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('206','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Wang, Qi;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('216','tp_links')\" style=\"cursor:pointer;\">Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Machine Learning, <\/span><span class=\"tp_pub_additional_year\">2022<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_216\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('216','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_216\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('216','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_216\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{wang2022model,<br \/>\r\ntitle = {Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search},<br \/>\r\nauthor = {Qi Wang and Herke Hoof},<br \/>\r\nurl = {https:\/\/drive.google.com\/file\/d\/1M9WO4Q-8h_iJ7vAyYTQjCRJki-zYS5Mu\/view},<br \/>\r\nyear  = {2022},<br \/>\r\ndate = {2022-07-17},<br \/>\r\nbooktitle = {International Conference on Machine Learning},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('216','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_216\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/drive.google.com\/file\/d\/1M9WO4Q-8h_iJ7vAyYTQjCRJki-zYS5Mu\/view\" title=\"https:\/\/drive.google.com\/file\/d\/1M9WO4Q-8h_iJ7vAyYTQjCRJki-zYS5Mu\/view\" target=\"_blank\">https:\/\/drive.google.com\/file\/d\/1M9WO4Q-8h_iJ7vAyYTQjCRJki-zYS5Mu\/view<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('216','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Kool, Wouter;  Hoof, Herke;  Gromicho, Joaquim;  Welling, Max<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('203','tp_links')\" style=\"cursor:pointer;\">Deep Policy Dynamic Programming for Vehicle Routing Problems<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research, <\/span><span class=\"tp_pub_additional_year\">2022<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_203\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('203','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_203\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('203','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_203\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{kool2022deep,<br \/>\r\ntitle = {Deep Policy Dynamic Programming for Vehicle Routing Problems},<br \/>\r\nauthor = {Wouter Kool and Herke Hoof and Joaquim Gromicho and Max Welling},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2102.11756},<br \/>\r\nyear  = {2022},<br \/>\r\ndate = {2022-06-20},<br \/>\r\nbooktitle = {International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('203','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_203\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2102.11756\" title=\"https:\/\/arxiv.org\/abs\/2102.11756\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2102.11756<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('203','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Pol, Elise;  Hoof, Herke;  Oliehoek, Frans;  Welling, Max<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('164','tp_links')\" style=\"cursor:pointer;\">Multi-Agent MDP Homomorphic Networks<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Conference on Learning Representations, <\/span><span class=\"tp_pub_additional_year\">2022<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_164\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('164','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_164\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('164','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_164\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{pol2022multi,<br \/>\r\ntitle = {Multi-Agent MDP Homomorphic Networks},<br \/>\r\nauthor = {Elise Pol and Herke Hoof and Frans Oliehoek and Max Welling},<br \/>\r\nurl = {https:\/\/openreview.net\/forum?id=H7HDG\u2013DJF0},<br \/>\r\nyear  = {2022},<br \/>\r\ndate = {2022-04-25},<br \/>\r\nurldate = {2022-04-25},<br \/>\r\nbooktitle = {Proceedings of the International Conference on Learning Representations},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('164','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_164\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/openreview.net\/forum?id=H7HDG\u2013DJF0\" title=\"https:\/\/openreview.net\/forum?id=H7HDG\u2013DJF0\" target=\"_blank\">https:\/\/openreview.net\/forum?id=H7HDG\u2013DJF0<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('164','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Long, Alex;  Blair, Alan;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('169','tp_links')\" style=\"cursor:pointer;\">Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">AAAI National Conference on Artificial Intelligence, <\/span><span class=\"tp_pub_additional_year\">2022<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_169\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('169','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_169\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('169','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_169\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{long2022fast,<br \/>\r\ntitle = {Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation},<br \/>\r\nauthor = {Alex Long and Alan Blair and Herke Hoof},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2203.03078 <br \/>\r\nhttps:\/\/www.aaai.org\/AAAI22Papers\/AAAI-8450.LongA.pdf},<br \/>\r\nyear  = {2022},<br \/>\r\ndate = {2022-02-21},<br \/>\r\nbooktitle = {AAAI National Conference on Artificial Intelligence},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('169','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_169\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2203.03078\" title=\"https:\/\/arxiv.org\/abs\/2203.03078\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2203.03078<\/a><\/li><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/www.aaai.org\/AAAI22Papers\/AAAI-8450.LongA.pdf\" title=\"https:\/\/www.aaai.org\/AAAI22Papers\/AAAI-8450.LongA.pdf\" target=\"_blank\">https:\/\/www.aaai.org\/AAAI22Papers\/AAAI-8450.LongA.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('169','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2021\">2021<\/h3><div class=\"tp_publication tp_publication_article\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Wang, Shihan;  Zhang, Chao;  Kr\u00f6se, Ben;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('205','tp_links')\" style=\"cursor:pointer;\">Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator<\/a> <span class=\"tp_pub_type article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">Journal of Medical Systems, <\/span><span class=\"tp_pub_additional_volume\">vol. 45, <\/span><span class=\"tp_pub_additional_number\">no. 102, <\/span><span class=\"tp_pub_additional_year\">2021<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_205\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('205','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_205\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('205','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_205\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{wang2021optimizing,<br \/>\r\ntitle = {Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator},<br \/>\r\nauthor = {Shihan Wang and Chao Zhang and Ben Kr\u00f6se and Herke Hoof},<br \/>\r\nurl = {https:\/\/link.springer.com\/article\/10.1007\/s1090177-021-163-0},<br \/>\r\ndoi = {https:\/\/doi.org\/10.1007\/s1090177-021-163-0},<br \/>\r\nyear  = {2021},<br \/>\r\ndate = {2021-10-18},<br \/>\r\njournal = {Journal of Medical Systems},<br \/>\r\nvolume = {45},<br \/>\r\nnumber = {102},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('205','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_205\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/link.springer.com\/article\/10.1007\/s1090177-021-163-0\" title=\"https:\/\/link.springer.com\/article\/10.1007\/s1090177-021-163-0\" target=\"_blank\">https:\/\/link.springer.com\/article\/10.1007\/s1090177-021-163-0<\/a><\/li><li><i class=\"ai ai-doi\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/dx.doi.org\/https:\/\/doi.org\/10.1007\/s1090177-021-163-0\" title=\"Follow DOI:https:\/\/doi.org\/10.1007\/s1090177-021-163-0\" target=\"_blank\">doi:https:\/\/doi.org\/10.1007\/s1090177-021-163-0<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('205','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Zhang, Yijie;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('170','tp_links')\" style=\"cursor:pointer;\">Deep Coherent Exploration For Continuous Control<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Machine Learning, <\/span><span class=\"tp_pub_additional_year\">2021<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_170\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('170','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_170\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('170','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_170\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{zhang2021deep,<br \/>\r\ntitle = {Deep Coherent Exploration For Continuous Control},<br \/>\r\nauthor = {Yijie Zhang and Herke Hoof},<br \/>\r\nurl = {http:\/\/proceedings.mlr.press\/v139\/zhang21t.html},<br \/>\r\nyear  = {2021},<br \/>\r\ndate = {2021-07-19},<br \/>\r\nbooktitle = {International Conference on Machine Learning},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('170','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_170\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/proceedings.mlr.press\/v139\/zhang21t.html\" title=\"http:\/\/proceedings.mlr.press\/v139\/zhang21t.html\" target=\"_blank\">http:\/\/proceedings.mlr.press\/v139\/zhang21t.html<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('170','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> W\u00f6hlke, J.;  Schmitt, F.;  Hoof, H.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('171','tp_links')\" style=\"cursor:pointer;\">Hierarchies of Planning and Reinforcement Learning for Robot Navigation<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">IEEE International Conference on Robotics and Automation, <\/span><span class=\"tp_pub_additional_year\">2021<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_171\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('171','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_171\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('171','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_171\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{woehlke2021hierarchies,<br \/>\r\ntitle = {Hierarchies of Planning and Reinforcement Learning for Robot Navigation},<br \/>\r\nauthor = {J. W\u00f6hlke and F. Schmitt and H. Hoof},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2109.11178},<br \/>\r\nyear  = {2021},<br \/>\r\ndate = {2021-05-30},<br \/>\r\nbooktitle = {IEEE International Conference on Robotics and Automation},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('171','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_171\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2109.11178\" title=\"https:\/\/arxiv.org\/abs\/2109.11178\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2109.11178<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('171','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_article\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Wang, S.;  Sporrel, K.;  Hoof, H.;  Simons, M.;  Boer, R.;  Ettema, D.;  Nibbeling, N.;  Deutekom, M.;  Kr\u00f6se, B.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('172','tp_links')\" style=\"cursor:pointer;\">Reinforcement Learning to Send Reminders at Right Moments in Smartphone Exercise Application: A Feasibility Study<\/a> <span class=\"tp_pub_type article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">International Journal of Environmental Research and Public Health, Special Issue, <\/span><span class=\"tp_pub_additional_year\">2021<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_172\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('172','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_172\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('172','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_172\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{wang2021reinforcement,<br \/>\r\ntitle = {Reinforcement Learning to Send Reminders at Right Moments in Smartphone Exercise Application: A Feasibility Study},<br \/>\r\nauthor = {S. Wang and K. Sporrel and H. Hoof and M. Simons and R. Boer and D. Ettema and N. Nibbeling and M. Deutekom and B. Kr\u00f6se},<br \/>\r\nurl = {https:\/\/www.mdpi.com\/1660-4601\/18\/11\/6059 <br \/>\r\nhttps:\/\/www.mdpi.com\/1660-4601\/18\/11\/6059\/pdf},<br \/>\r\nyear  = {2021},<br \/>\r\ndate = {2021-04-06},<br \/>\r\njournal = {International Journal of Environmental Research and Public Health, Special Issue},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('172','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_172\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/www.mdpi.com\/1660-4601\/18\/11\/6059\" title=\"https:\/\/www.mdpi.com\/1660-4601\/18\/11\/6059\" target=\"_blank\">https:\/\/www.mdpi.com\/1660-4601\/18\/11\/6059<\/a><\/li><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/www.mdpi.com\/1660-4601\/18\/11\/6059\/pdf\" title=\"https:\/\/www.mdpi.com\/1660-4601\/18\/11\/6059\/pdf\" target=\"_blank\">https:\/\/www.mdpi.com\/1660-4601\/18\/11\/6059\/pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('172','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2020\">2020<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Pol, Elise;  Worrall, Daniel;  Hoof, Herke;  Oliehoek, Frans;  Welling, Max<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('211','tp_links')\" style=\"cursor:pointer;\">MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Advances in Neural Information Processing Systems, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_211\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('211','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_211\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('211','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_211\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{pol2020mdp,<br \/>\r\ntitle = {MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning},<br \/>\r\nauthor = {Elise Pol and Daniel Worrall and Herke Hoof and Frans Oliehoek and Max Welling},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2006.16908 <br \/>\r\nhttps:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/2be5f9c2e3620eb73c2972d7552b6cb5-Abstract.html},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-12-02},<br \/>\r\nbooktitle = {Advances in Neural Information Processing Systems},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('211','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_211\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2006.16908\" title=\"https:\/\/arxiv.org\/abs\/2006.16908\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2006.16908<\/a><\/li><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/2be5f9c2e3620eb73c2972d7552b6cb5-Abstract.html\" title=\"https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/2be5f9c2e3620eb73c2972d7552b6cb5-[...]\" target=\"_blank\">https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/2be5f9c2e3620eb73c2972d7552b6cb5-[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('211','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Bakker, Tim;  Hoof, Herke;  Welling, Max<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('212','tp_links')\" style=\"cursor:pointer;\">Experimental design for MRI by greedy policy search<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Advances in Neural Information Processing Systems, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_212\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('212','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_212\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('212','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_212\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{bakker2020experimental,<br \/>\r\ntitle = {Experimental design for MRI by greedy policy search},<br \/>\r\nauthor = {Tim Bakker and Herke Hoof and Max Welling},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2010.16262 <br \/>\r\nhttps:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/daed210307f1dbc6f1dd9551408d999f-Abstract.html},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-12-02},<br \/>\r\nbooktitle = {Advances in Neural Information Processing Systems},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('212','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_212\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2010.16262\" title=\"https:\/\/arxiv.org\/abs\/2010.16262\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2010.16262<\/a><\/li><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/daed210307f1dbc6f1dd9551408d999f-Abstract.html\" title=\"https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/daed210307f1dbc6f1dd9551408d999f-[...]\" target=\"_blank\">https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/daed210307f1dbc6f1dd9551408d999f-[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('212','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Huang, Jin;  Oosterhuis, Harrie;  Rijke, Maarten;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('168','tp_links')\" style=\"cursor:pointer;\">Keeping Dataset Biases out of the Simulation: A Debiased Simulator for Reinforcement Learning based Recommender Systems<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">The ACM Conference on Recommender Systems, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_168\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('168','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_168\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('168','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_168\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{huang2020keeping,<br \/>\r\ntitle = {Keeping Dataset Biases out of the Simulation: A Debiased Simulator for Reinforcement Learning based Recommender Systems},<br \/>\r\nauthor = {Jin Huang and Harrie Oosterhuis and Maarten Rijke and Herke Hoof},<br \/>\r\nurl = {https:\/\/dl.acm.org\/doi\/10.1145\/3383313.3412252 <br \/>\r\nhttps:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-content\/papercite-data\/pdf\/huang-2020-keeping.pdf},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-09-22},<br \/>\r\nbooktitle = {The ACM Conference on Recommender Systems},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('168','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_168\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3383313.3412252\" title=\"https:\/\/dl.acm.org\/doi\/10.1145\/3383313.3412252\" target=\"_blank\">https:\/\/dl.acm.org\/doi\/10.1145\/3383313.3412252<\/a><\/li><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-content\/papercite-data\/pdf\/huang-2020-keeping.pdf\" title=\"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-content\/papercite-data\/pdf\/huang-2020-kee[...]\" target=\"_blank\">https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-content\/papercite-data\/pdf\/huang-2020-kee[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('168','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Heide, Tessa;  Mirus, Florian;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('208','tp_links')\" style=\"cursor:pointer;\">Social Navigation with Human Empowerment Driven Reinforcement Learning<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Artificial Neural Networks, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_208\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('208','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_208\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('208','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_208\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{heide2020social,<br \/>\r\ntitle = {Social Navigation with Human Empowerment Driven Reinforcement Learning},<br \/>\r\nauthor = {Tessa Heide and Florian Mirus and Herke Hoof},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2003.08158},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-09-15},<br \/>\r\nbooktitle = {International Conference on Artificial Neural Networks},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('208','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_208\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2003.08158\" title=\"https:\/\/arxiv.org\/abs\/2003.08158\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2003.08158<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('208','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_article\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Akata, Zeynep;  Balliet, Dan;  Rijke, Maarten;  Dignum, Frank;  Dignum, Virginia;  Eiben, Guszti;  others,<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('209','tp_links')\" style=\"cursor:pointer;\">A Research Agenda for Hybrid Intelligence: Augmenting Human Intellect With Collaborative, Adaptive, Responsible, and Explainable Artificial Intelligence<\/a> <span class=\"tp_pub_type article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">Computer, <\/span><span class=\"tp_pub_additional_volume\">vol. 53, <\/span><span class=\"tp_pub_additional_number\">no. 8, <\/span><span class=\"tp_pub_additional_pages\">pp. 18\u201328, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_209\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('209','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_209\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('209','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_209\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{akata2020research,<br \/>\r\ntitle = {A Research Agenda for Hybrid Intelligence: Augmenting Human Intellect With Collaborative, Adaptive, Responsible, and Explainable Artificial Intelligence},<br \/>\r\nauthor = {Zeynep Akata and Dan Balliet and Maarten Rijke and Frank Dignum and Virginia Dignum and Guszti Eiben and others},<br \/>\r\nurl = {https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-content\/papercite-data\/pdf\/akata-2020-research.pdf},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-08-12},<br \/>\r\njournal = {Computer},<br \/>\r\nvolume = {53},<br \/>\r\nnumber = {8},<br \/>\r\npages = {18\u201328},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('209','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_209\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-content\/papercite-data\/pdf\/akata-2020-research.pdf\" title=\"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-content\/papercite-data\/pdf\/akata-2020-res[...]\" target=\"_blank\">https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-content\/papercite-data\/pdf\/akata-2020-res[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('209','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Wang, Qi;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('210','tp_links')\" style=\"cursor:pointer;\">Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Machine Learning, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_210\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('210','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_210\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('210','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_210\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{wang2020doubly,<br \/>\r\ntitle = {Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables},<br \/>\r\nauthor = {Qi Wang and Herke Hoof},<br \/>\r\nurl = {https:\/\/proceedings.icml.cc\/static\/paper_files\/icml\/2020\/2280-Paper.pdf},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-07-12},<br \/>\r\nbooktitle = {International Conference on Machine Learning},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('210','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_210\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/proceedings.icml.cc\/static\/paper_files\/icml\/2020\/2280-Paper.pdf\" title=\"https:\/\/proceedings.icml.cc\/static\/paper_files\/icml\/2020\/2280-Paper.pdf\" target=\"_blank\">https:\/\/proceedings.icml.cc\/static\/paper_files\/icml\/2020\/2280-Paper.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('210','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Mollinga, Jasper;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('167','tp_links')\" style=\"cursor:pointer;\">An Autonomous Free Airspace En-route Controller using Deep Reinforcement Learning Techniques<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Research in Air Transportation, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_167\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('167','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_167\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('167','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_167\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{mollinga2020autonomous,<br \/>\r\ntitle = {An Autonomous Free Airspace En-route Controller using Deep Reinforcement Learning Techniques},<br \/>\r\nauthor = {Jasper Mollinga and Herke Hoof},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2007.01599},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-06-23},<br \/>\r\nbooktitle = {International Conference on Research in Air Transportation},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('167','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_167\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2007.01599\" title=\"https:\/\/arxiv.org\/abs\/2007.01599\" target=\"_blank\">https:\/\/arxiv.org\/abs\/2007.01599<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('167','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> W\u00f6hlke, Jan;  Schmitt, Felix;  Hoof, Herke<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('173','tp_links')\" style=\"cursor:pointer;\">A Performance-Based Start State Curriculum Framework for Reinforcement Learning<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Autonomous Agents and Multi-Agent Systems, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_173\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('173','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_173\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('173','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_173\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{woehlke2020performance,<br \/>\r\ntitle = {A Performance-Based Start State Curriculum Framework for Reinforcement Learning},<br \/>\r\nauthor = {Jan W\u00f6hlke and Felix Schmitt and Herke Hoof},<br \/>\r\nurl = {http:\/\/ifaamas.org\/Proceedings\/aamas2020\/pdfs\/p1503.pdf},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-05-09},<br \/>\r\nbooktitle = {International Conference on Autonomous Agents and Multi-Agent Systems},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('173','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_173\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/ifaamas.org\/Proceedings\/aamas2020\/pdfs\/p1503.pdf\" title=\"http:\/\/ifaamas.org\/Proceedings\/aamas2020\/pdfs\/p1503.pdf\" target=\"_blank\">http:\/\/ifaamas.org\/Proceedings\/aamas2020\/pdfs\/p1503.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('173','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Kool, Wouter;  Hoof, Herke;  Welling, Max<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('174','tp_links')\" style=\"cursor:pointer;\">Estimating Gradients for Discrete Random Variables by Sampling without Replacement<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Learning Representations, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_174\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('174','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_174\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('174','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_174\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{kool2020estimating,<br \/>\r\ntitle = {Estimating Gradients for Discrete Random Variables by Sampling without Replacement},<br \/>\r\nauthor = {Wouter Kool and Herke Hoof and Max Welling},<br \/>\r\nurl = {https:\/\/openreview.net\/pdf?id=rklEj2EFvB <br \/>\r\nhttps:\/\/youtu.be\/KtP-Z2bvPPE},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-04-26},<br \/>\r\nurldate = {2020-04-26},<br \/>\r\nbooktitle = {International Conference on Learning Representations},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('174','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_174\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/openreview.net\/pdf?id=rklEj2EFvB\" title=\"https:\/\/openreview.net\/pdf?id=rklEj2EFvB\" target=\"_blank\">https:\/\/openreview.net\/pdf?id=rklEj2EFvB<\/a><\/li><li><i class=\"fab fa-youtube\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/youtu.be\/KtP-Z2bvPPE\" title=\"https:\/\/youtu.be\/KtP-Z2bvPPE\" target=\"_blank\">https:\/\/youtu.be\/KtP-Z2bvPPE<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('174','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_article\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Kool, W.;  Hoof, H.;  Welling, M.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('175','tp_links')\" style=\"cursor:pointer;\">Ancestral Gumbel-Top-k Sampling for Sampling without Replacement<\/a> <span class=\"tp_pub_type article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">Journal of Machine Learning Research, <\/span><span class=\"tp_pub_additional_volume\">vol. 21, <\/span><span class=\"tp_pub_additional_number\">no. 47, <\/span><span class=\"tp_pub_additional_pages\">pp. 1\u201336, <\/span><span class=\"tp_pub_additional_year\">2020<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_175\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('175','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_175\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('175','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_175\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{kool2020ancestral,<br \/>\r\ntitle = {Ancestral Gumbel-Top-k Sampling for Sampling without Replacement},<br \/>\r\nauthor = {W. Kool and H. Hoof and M. Welling},<br \/>\r\nurl = {http:\/\/jmlr.org\/papers\/volume21\/19-985\/19-985.pdf},<br \/>\r\nyear  = {2020},<br \/>\r\ndate = {2020-03-10},<br \/>\r\njournal = {Journal of Machine Learning Research},<br \/>\r\nvolume = {21},<br \/>\r\nnumber = {47},<br \/>\r\npages = {1\u201336},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('175','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_175\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/jmlr.org\/papers\/volume21\/19-985\/19-985.pdf\" title=\"http:\/\/jmlr.org\/papers\/volume21\/19-985\/19-985.pdf\" target=\"_blank\">http:\/\/jmlr.org\/papers\/volume21\/19-985\/19-985.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('175','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2019\">2019<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Caccia, Lucas;  Hoof, Herke;  Courville, Aaron C.;  Pineau, Joelle<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('176','tp_links')\" style=\"cursor:pointer;\">Deep Generative Modeling of LiDAR Data<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">IEEE International Conference on Intelligent Robots and Systems, <\/span><span class=\"tp_pub_additional_year\">2019<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_176\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('176','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_176\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('176','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_176\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{page2019deep,<br \/>\r\ntitle = {Deep Generative Modeling of LiDAR Data},<br \/>\r\nauthor = {Lucas Caccia and Herke Hoof and Aaron C. Courville and Joelle Pineau},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/1812.01180},<br \/>\r\nyear  = {2019},<br \/>\r\ndate = {2019-11-04},<br \/>\r\nbooktitle = {IEEE International Conference on Intelligent Robots and Systems},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('176','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_176\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/1812.01180\" title=\"https:\/\/arxiv.org\/abs\/1812.01180\" target=\"_blank\">https:\/\/arxiv.org\/abs\/1812.01180<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('176','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Shang, Wenling;  Wal, Douwe;  Hoof, Herke;  Welling, Max<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('177','tp_links')\" style=\"cursor:pointer;\">Stochastic Activation Actor Critic Methods<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">European Conference on Machine Learning, <\/span><span class=\"tp_pub_additional_year\">2019<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_177\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('177','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_177\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('177','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_177\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{shang2019stochastic,<br \/>\r\ntitle = {Stochastic Activation Actor Critic Methods},<br \/>\r\nauthor = {Wenling Shang and Douwe Wal and Herke Hoof and Max Welling},<br \/>\r\nurl = {https:\/\/ecmlpkdd2019.org\/downloads\/paper\/483.pdf},<br \/>\r\nyear  = {2019},<br \/>\r\ndate = {2019-09-16},<br \/>\r\nbooktitle = {European Conference on Machine Learning},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('177','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_177\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/ecmlpkdd2019.org\/downloads\/paper\/483.pdf\" title=\"https:\/\/ecmlpkdd2019.org\/downloads\/paper\/483.pdf\" target=\"_blank\">https:\/\/ecmlpkdd2019.org\/downloads\/paper\/483.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('177','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Kool, Wouter;  Hoof, Herke Van;  Welling, Max<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('178','tp_links')\" style=\"cursor:pointer;\">Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Machine Learning, <\/span><span class=\"tp_pub_additional_pages\">pp. 3499\u20133508, <\/span><span class=\"tp_pub_additional_year\">2019<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_178\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('178','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_178\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('178','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_178\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{kool2019stochastic,<br \/>\r\ntitle = {Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement},<br \/>\r\nauthor = {Wouter Kool and Herke Van Hoof and Max Welling},<br \/>\r\nurl = {http:\/\/proceedings.mlr.press\/v97\/kool19a\/kool19a.pdf <br \/>\r\nhttp:\/\/proceedings.mlr.press\/v97\/kool19a\/kool19a-supp.pdf},<br \/>\r\nyear  = {2019},<br \/>\r\ndate = {2019-06-10},<br \/>\r\nurldate = {2019-06-10},<br \/>\r\nbooktitle = {International Conference on Machine Learning},<br \/>\r\npages = {3499\u20133508},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('178','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_178\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/proceedings.mlr.press\/v97\/kool19a\/kool19a.pdf\" title=\"http:\/\/proceedings.mlr.press\/v97\/kool19a\/kool19a.pdf\" target=\"_blank\">http:\/\/proceedings.mlr.press\/v97\/kool19a\/kool19a.pdf<\/a><\/li><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/proceedings.mlr.press\/v97\/kool19a\/kool19a-supp.pdf\" title=\"http:\/\/proceedings.mlr.press\/v97\/kool19a\/kool19a-supp.pdf\" target=\"_blank\">http:\/\/proceedings.mlr.press\/v97\/kool19a\/kool19a-supp.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('178','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Thakur, S.;  Hoof, H.;  Higuera, J. C. Gamboa;  Precup, D.;  Meger, D.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('204','tp_links')\" style=\"cursor:pointer;\">Uncertainty aware Imitation Learning on Multiple Tasks using Bayesian Neural Networks<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Robotics and Automation, <\/span><span class=\"tp_pub_additional_year\">2019<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_204\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('204','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_204\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('204','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_204\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{thakur2019uncertainty,<br \/>\r\ntitle = {Uncertainty aware Imitation Learning on Multiple Tasks using Bayesian Neural Networks},<br \/>\r\nauthor = {S. Thakur and H. Hoof and J. C. Gamboa Higuera and D. Precup and D. Meger},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/1903.05697},<br \/>\r\nyear  = {2019},<br \/>\r\ndate = {2019-05-20},<br \/>\r\nbooktitle = {International Conference on Robotics and Automation},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('204','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_204\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/1903.05697\" title=\"https:\/\/arxiv.org\/abs\/1903.05697\" target=\"_blank\">https:\/\/arxiv.org\/abs\/1903.05697<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('204','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Kool, Wouter;  Hoof, Herke;  Welling, Max<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('179','tp_links')\" style=\"cursor:pointer;\">Attention! Learn to solve routing problems!<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Learning Representations, <\/span><span class=\"tp_pub_additional_year\">2019<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_179\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('179','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_179\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('179','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_179\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{kool2019attention,<br \/>\r\ntitle = {Attention! Learn to solve routing problems!},<br \/>\r\nauthor = {Wouter Kool and Herke Hoof and Max Welling},<br \/>\r\nurl = {https:\/\/openreview.net\/pdf?id=ByxBFsRqYm},<br \/>\r\nyear  = {2019},<br \/>\r\ndate = {2019-05-06},<br \/>\r\nbooktitle = {International Conference on Learning Representations},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('179','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_179\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/openreview.net\/pdf?id=ByxBFsRqYm\" title=\"https:\/\/openreview.net\/pdf?id=ByxBFsRqYm\" target=\"_blank\">https:\/\/openreview.net\/pdf?id=ByxBFsRqYm<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('179','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2018\">2018<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Manjanna, S.;  Hoof, H.;  Dudek, G.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('180','tp_links')\" style=\"cursor:pointer;\">Policy Search on Aggregated State Space for Active Sampling<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Symposium on Experimental Robotics, <\/span><span class=\"tp_pub_additional_year\">2018<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_180\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('180','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_180\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('180','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_180\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{manjannab,<br \/>\r\ntitle = {Policy Search on Aggregated State Space for Active Sampling},<br \/>\r\nauthor = {S. Manjanna and H. Hoof and G. Dudek},<br \/>\r\nurl = {http:\/\/www.cim.mcgill.ca\/~mrl\/pubs\/sandeep\/ISER2018.pdf},<br \/>\r\nyear  = {2018},<br \/>\r\ndate = {2018-11-05},<br \/>\r\nbooktitle = {International Symposium on Experimental Robotics},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('180','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_180\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.cim.mcgill.ca\/~mrl\/pubs\/sandeep\/ISER2018.pdf\" title=\"http:\/\/www.cim.mcgill.ca\/~mrl\/pubs\/sandeep\/ISER2018.pdf\" target=\"_blank\">http:\/\/www.cim.mcgill.ca\/~mrl\/pubs\/sandeep\/ISER2018.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('180','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Dong, Y.;  Shen, Y.;  Crawford, E.;  Hoof, H.;  Cheung, J. C. K.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('181','tp_links')\" style=\"cursor:pointer;\">BanditSum: Extractive Summarization as a Contextual Bandit<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Conference on Empirical Methods in Natural Language Processing (EMNLP), <\/span><span class=\"tp_pub_additional_pages\">pp. 3739\u20133748, <\/span><span class=\"tp_pub_additional_year\">2018<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_181\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('181','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_181\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('181','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_181\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{dong2018bandit,<br \/>\r\ntitle = {BanditSum: Extractive Summarization as a Contextual Bandit},<br \/>\r\nauthor = {Y. Dong and Y. Shen and E. Crawford and H. Hoof and J. C. K. Cheung},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/1809.09672 <br \/>\r\nhttp:\/\/www.aclweb.org\/anthology\/D18-1409},<br \/>\r\nyear  = {2018},<br \/>\r\ndate = {2018-10-31},<br \/>\r\nbooktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)},<br \/>\r\npages = {3739\u20133748},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('181','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_181\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/1809.09672\" title=\"https:\/\/arxiv.org\/abs\/1809.09672\" target=\"_blank\">https:\/\/arxiv.org\/abs\/1809.09672<\/a><\/li><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.aclweb.org\/anthology\/D18-1409\" title=\"http:\/\/www.aclweb.org\/anthology\/D18-1409\" target=\"_blank\">http:\/\/www.aclweb.org\/anthology\/D18-1409<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('181','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Manjanna, S.;  Hoof, H.;  Dudek, G.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('182','tp_links')\" style=\"cursor:pointer;\">Reinforcement Learning with Non-uniform State Representations for Adaptive Search<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">IEEE International Symposium on Safety, Security, and Rescue Robotics, <\/span><span class=\"tp_pub_additional_year\">2018<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_182\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('182','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_182\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('182','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_182\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{manjanna2018reinforcement,<br \/>\r\ntitle = {Reinforcement Learning with Non-uniform State Representations for Adaptive Search},<br \/>\r\nauthor = {S. Manjanna and H. Hoof and G. Dudek},<br \/>\r\nurl = {http:\/\/www.cim.mcgill.ca\/~mrl\/pubs\/sandeep\/SSRR2018.pdf},<br \/>\r\nyear  = {2018},<br \/>\r\ndate = {2018-08-06},<br \/>\r\nbooktitle = {IEEE International Symposium on Safety, Security, and Rescue Robotics},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('182','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_182\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.cim.mcgill.ca\/~mrl\/pubs\/sandeep\/SSRR2018.pdf\" title=\"http:\/\/www.cim.mcgill.ca\/~mrl\/pubs\/sandeep\/SSRR2018.pdf\" target=\"_blank\">http:\/\/www.cim.mcgill.ca\/~mrl\/pubs\/sandeep\/SSRR2018.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('182','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Fujimoto, S.;  Hoof, H.;  Meger, D.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('183','tp_links')\" style=\"cursor:pointer;\">Addressing function approximation error in actor-critic methods<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Machine Learning, <\/span><span class=\"tp_pub_additional_pages\">pp. 1587\u20131596, <\/span><span class=\"tp_pub_additional_year\">2018<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_183\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('183','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_183\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('183','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_183\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{fujimoto2018addressing,<br \/>\r\ntitle = {Addressing function approximation error in actor-critic methods},<br \/>\r\nauthor = {S. Fujimoto and H. Hoof and D. Meger},<br \/>\r\nurl = {http:\/\/proceedings.mlr.press\/v80\/fujimoto18a\/fujimoto18a.pdf <br \/>\r\nhttp:\/\/proceedings.mlr.press\/v80\/fujimoto18a\/fujimoto18a-supp.pdf},<br \/>\r\nyear  = {2018},<br \/>\r\ndate = {2018-07-10},<br \/>\r\nbooktitle = {International Conference on Machine Learning},<br \/>\r\npages = {1587\u20131596},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('183','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_183\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/proceedings.mlr.press\/v80\/fujimoto18a\/fujimoto18a.pdf\" title=\"http:\/\/proceedings.mlr.press\/v80\/fujimoto18a\/fujimoto18a.pdf\" target=\"_blank\">http:\/\/proceedings.mlr.press\/v80\/fujimoto18a\/fujimoto18a.pdf<\/a><\/li><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/proceedings.mlr.press\/v80\/fujimoto18a\/fujimoto18a-supp.pdf\" title=\"http:\/\/proceedings.mlr.press\/v80\/fujimoto18a\/fujimoto18a-supp.pdf\" target=\"_blank\">http:\/\/proceedings.mlr.press\/v80\/fujimoto18a\/fujimoto18a-supp.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('183','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Smith, M.;  Hoof, H.;  Pineau, J.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('184','tp_links')\" style=\"cursor:pointer;\">An Inference-Based Policy Gradient Method for Learning Options<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Machine Learning, <\/span><span class=\"tp_pub_additional_pages\">pp. 4703-4712, <\/span><span class=\"tp_pub_additional_year\">2018<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_184\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('184','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_184\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('184','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_184\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{smith2018inference,<br \/>\r\ntitle = {An Inference-Based Policy Gradient Method for Learning Options},<br \/>\r\nauthor = {M. Smith and H. Hoof and J. Pineau},<br \/>\r\nurl = {http:\/\/proceedings.mlr.press\/v80\/smith18a\/smith18a.pdf},<br \/>\r\nyear  = {2018},<br \/>\r\ndate = {2018-07-10},<br \/>\r\nurldate = {2018-07-10},<br \/>\r\nbooktitle = {International Conference on Machine Learning},<br \/>\r\npages = {4703-4712},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('184','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_184\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/proceedings.mlr.press\/v80\/smith18a\/smith18a.pdf\" title=\"http:\/\/proceedings.mlr.press\/v80\/smith18a\/smith18a.pdf\" target=\"_blank\">http:\/\/proceedings.mlr.press\/v80\/smith18a\/smith18a.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('184','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Barbaros, V.;  Hoof, H.;  Abdolmaleki, A.;  Meger, D.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('185','tp_links')\" style=\"cursor:pointer;\">Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Robotics and Automation, <\/span><span class=\"tp_pub_additional_year\">2018<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_185\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('185','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_185\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('185','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_185\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{2018barbaroscomparison,<br \/>\r\ntitle = {Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control},<br \/>\r\nauthor = {V. Barbaros and H. Hoof and A. Abdolmaleki and D. Meger},<br \/>\r\nurl = {https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/files\/barbaros2018eager.pdf},<br \/>\r\nyear  = {2018},<br \/>\r\ndate = {2018-05-21},<br \/>\r\nurldate = {2018-05-21},<br \/>\r\nbooktitle = {International Conference on Robotics and Automation},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('185','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_185\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/files\/barbaros2018eager.pdf\" title=\"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/files\/barbaros2018eager.pdf\" target=\"_blank\">https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/files\/barbaros2018eager.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('185','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2017\">2017<\/h3><div class=\"tp_publication tp_publication_article\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, H. Van;  Neumann, G.;  Peters, J.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('186','tp_links')\" style=\"cursor:pointer;\">Non-parametric Policy Search with Limited Information Loss<\/a> <span class=\"tp_pub_type article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">Journal of Machine Learning Research, <\/span><span class=\"tp_pub_additional_volume\">vol. 18, <\/span><span class=\"tp_pub_additional_number\">no. 73, <\/span><span class=\"tp_pub_additional_pages\">pp. 1-46, <\/span><span class=\"tp_pub_additional_year\">2017<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_186\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('186','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_186\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('186','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_186\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{hoof2017nonparametric,<br \/>\r\ntitle = {Non-parametric Policy Search with Limited Information Loss},<br \/>\r\nauthor = {H. Van Hoof and G. Neumann and J. Peters},<br \/>\r\neditor = {K. Murphy},<br \/>\r\nurl = {http:\/\/jmlr.org\/papers\/volume18\/16-142\/16-142.pdf},<br \/>\r\nyear  = {2017},<br \/>\r\ndate = {2017-08-01},<br \/>\r\njournal = {Journal of Machine Learning Research},<br \/>\r\nvolume = {18},<br \/>\r\nnumber = {73},<br \/>\r\npages = {1-46},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('186','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_186\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/jmlr.org\/papers\/volume18\/16-142\/16-142.pdf\" title=\"http:\/\/jmlr.org\/papers\/volume18\/16-142\/16-142.pdf\" target=\"_blank\">http:\/\/jmlr.org\/papers\/volume18\/16-142\/16-142.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('186','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_article\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, Herke;  Tanneberg, Daniel;  Peters, Jan<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('187','tp_links')\" style=\"cursor:pointer;\">Generalized Exploration in Policy Search<\/a> <span class=\"tp_pub_type article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">Machine Learning - Special issue ECML PKDD, <\/span><span class=\"tp_pub_additional_volume\">vol. 106, <\/span><span class=\"tp_pub_additional_number\">no. 9\u201310, <\/span><span class=\"tp_pub_additional_pages\">pp. 1705\u20131724, <\/span><span class=\"tp_pub_additional_year\">2017<\/span>, <span class=\"tp_pub_additional_issn\">ISSN: 1573-0565<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_187\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('187','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_187\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('187','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_187\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{hoof2017generalized,<br \/>\r\ntitle = {Generalized Exploration in Policy Search},<br \/>\r\nauthor = {Herke Hoof and Daniel Tanneberg and Jan Peters},<br \/>\r\neditor = {Kurt Driessens and Marko Dragi Kocev and Robnik-v Sikonja and Myra Spiliopoulou},<br \/>\r\nurl = {http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/vanHoof_MLJ_2017.pdf},<br \/>\r\ndoi = {10.1007\/s1095657-017-94-1},<br \/>\r\nissn = {1573-0565},<br \/>\r\nyear  = {2017},<br \/>\r\ndate = {2017-07-13},<br \/>\r\njournal = {Machine Learning - Special issue ECML PKDD},<br \/>\r\nvolume = {106},<br \/>\r\nnumber = {9\u201310},<br \/>\r\npages = {1705\u20131724},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('187','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_187\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/vanHoof_MLJ_2017.pdf\" title=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/vanHoof_MLJ_2017.pd[...]\" target=\"_blank\">http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/vanHoof_MLJ_2017.pd[...]<\/a><\/li><li><i class=\"ai ai-doi\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/dx.doi.org\/10.1007\/s1095657-017-94-1\" title=\"Follow DOI:10.1007\/s1095657-017-94-1\" target=\"_blank\">doi:10.1007\/s1095657-017-94-1<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('187','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Tangkaratt, V.;  Hoof, H.;  Parisi, S.;  Neumann, G.;  Peters, J.;  Sugiyama, M.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('188','tp_links')\" style=\"cursor:pointer;\">Policy Search with High-Dimensional Context Variables<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), <\/span><span class=\"tp_pub_additional_pages\">pp. 2632\u20132638, <\/span><span class=\"tp_pub_additional_year\">2017<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_188\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('188','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_188\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('188','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_188\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{tangkaratt2017policy,<br \/>\r\ntitle = {Policy Search with High-Dimensional Context Variables},<br \/>\r\nauthor = {V. Tangkaratt and H. Hoof and S. Parisi and G. Neumann and J. Peters and M. Sugiyama},<br \/>\r\nurl = {http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/tangkaratt2017policy.pdf},<br \/>\r\nyear  = {2017},<br \/>\r\ndate = {2017-01-01},<br \/>\r\nbooktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},<br \/>\r\npages = {2632\u20132638},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('188','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_188\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/tangkaratt2017policy.pdf\" title=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/tangkaratt2017polic[...]\" target=\"_blank\">http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/tangkaratt2017polic[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('188','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2016\">2016<\/h3><div class=\"tp_publication tp_publication_article\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Daniel, Christian;  Hoof, Herke;  Neumann, Gerhard;  Peters, Jan<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('189','tp_links')\" style=\"cursor:pointer;\">Probabilistic Inference for Determining Options in Reinforcement Learning<\/a> <span class=\"tp_pub_type article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">Machine Learning - Special issue ECML PKDD, <\/span><span class=\"tp_pub_additional_volume\">vol. 104, <\/span><span class=\"tp_pub_additional_number\">no. 2\u20133, <\/span><span class=\"tp_pub_additional_pages\">pp. 337\u2013357, <\/span><span class=\"tp_pub_additional_year\">2016<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_189\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('189','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_189\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('189','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_189\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{daniel2016probabilistic,<br \/>\r\ntitle = {Probabilistic Inference for Determining Options in Reinforcement Learning},<br \/>\r\nauthor = {Christian Daniel and Herke Hoof and Gerhard Neumann and Jan Peters},<br \/>\r\nurl = {https:\/\/www.researchgate.net\/profile\/Jan_Peters4\/publication\/305789196_Probabilistic_inference_for_determining_options_in_reinforcement_learning\/links\/57d15f3008ae6399a38b4302.pdf},<br \/>\r\nyear  = {2016},<br \/>\r\ndate = {2016-01-01},<br \/>\r\njournal = {Machine Learning - Special issue ECML PKDD},<br \/>\r\nvolume = {104},<br \/>\r\nnumber = {2\u20133},<br \/>\r\npages = {337\u2013357},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('189','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_189\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/www.researchgate.net\/profile\/Jan_Peters4\/publication\/305789196_Probabilistic_inference_for_determining_options_in_reinforcement_learning\/links\/57d15f3008ae6399a38b4302.pdf\" title=\"https:\/\/www.researchgate.net\/profile\/Jan_Peters4\/publication\/305789196_Probabili[...]\" target=\"_blank\">https:\/\/www.researchgate.net\/profile\/Jan_Peters4\/publication\/305789196_Probabili[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('189','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, Herke;  Chen, Nutan;  Karl, Maximilian;  Smart, Patrick;  Peters, Jan<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('190','tp_links')\" style=\"cursor:pointer;\">Stable Reinforcement Learning with Auto-Encoders for Tactile and Visual Data<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Intelligent Robots and Systems, <\/span><span class=\"tp_pub_additional_pages\">pp. 3928\u20133934, <\/span><span class=\"tp_pub_additional_year\">2016<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_190\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('190','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_190\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('190','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_190\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{hoof2016stable,<br \/>\r\ntitle = {Stable Reinforcement Learning with Auto-Encoders for Tactile and Visual Data},<br \/>\r\nauthor = {Herke Hoof and Nutan Chen and Maximilian Karl and Patrick Smart and Jan Peters},<br \/>\r\nurl = {https:\/\/www.researchgate.net\/profile\/Patrick_Van_der_Smagt2\/publication\/305725116_Stable_Reinforcement_Learning_with_Autoencoders_for_Tactile_and_Visual_Data\/links\/579cfd5f08ae6a2882f2e8f1.pdf},<br \/>\r\nyear  = {2016},<br \/>\r\ndate = {2016-01-01},<br \/>\r\nbooktitle = {International Conference on Intelligent Robots and Systems},<br \/>\r\npages = {3928\u20133934},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('190','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_190\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/www.researchgate.net\/profile\/Patrick_Van_der_Smagt2\/publication\/305725116_Stable_Reinforcement_Learning_with_Autoencoders_for_Tactile_and_Visual_Data\/links\/579cfd5f08ae6a2882f2e8f1.pdf\" title=\"https:\/\/www.researchgate.net\/profile\/Patrick_Van_der_Smagt2\/publication\/30572511[...]\" target=\"_blank\">https:\/\/www.researchgate.net\/profile\/Patrick_Van_der_Smagt2\/publication\/30572511[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('190','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Yi, Z.;  Calandra, R.;  Veiga, F.;  Hoof, H.;  Hermans, T.;  Zhang, Y.;  Peters, J.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('192','tp_links')\" style=\"cursor:pointer;\">Active Tactile Object Exploration with Gaussian Processes<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the IEEE\/RSJ Conference on Intelligent Robots and Systems (IROS), <\/span><span class=\"tp_pub_additional_pages\">pp. 4925\u20134930, <\/span><span class=\"tp_pub_additional_year\">2016<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_192\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('192','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_192\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('192','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_192\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{iros2016yi,<br \/>\r\ntitle = {Active Tactile Object Exploration with Gaussian Processes},<br \/>\r\nauthor = {Z. Yi and R. Calandra and F. Veiga and H. Hoof and T. Hermans and Y. Zhang and J. Peters},<br \/>\r\nurl = {http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Publications\/Other\/iros2016yi.pdf},<br \/>\r\nyear  = {2016},<br \/>\r\ndate = {2016-01-01},<br \/>\r\nbooktitle = {Proceedings of the IEEE\/RSJ Conference on Intelligent Robots and Systems (IROS)},<br \/>\r\npages = {4925\u20134930},<br \/>\r\ncrossref = {p10958},<br \/>\r\nkey = {tacman, tactile manipulation},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('192','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_192\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Publications\/Other\/iros2016yi.pdf\" title=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Publications\/Other\/iros2016yi.pdf\" target=\"_blank\">http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Publications\/Other\/iros2016yi.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('192','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2015\">2015<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, Herke;  Peters, Jan;  Neumann, Gerhard<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('193','tp_links')\" style=\"cursor:pointer;\">Learning of Non-Parametric Control Policies with High-Dimensional State Features<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">International Conference on Artificial Intelligence and Statistics, <\/span><span class=\"tp_pub_additional_pages\">pp. 1004\u20131012, <\/span><span class=\"tp_pub_additional_year\">2015<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_193\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('193','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_193\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('193','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_193\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{hoof2015learning,<br \/>\r\ntitle = {Learning of Non-Parametric Control Policies with High-Dimensional State Features},<br \/>\r\nauthor = {Herke Hoof and Jan Peters and Gerhard Neumann},<br \/>\r\nurl = {http:\/\/www.jmlr.org\/proceedings\/papers\/v38\/vanhoof15.pdf},<br \/>\r\nyear  = {2015},<br \/>\r\ndate = {2015-01-01},<br \/>\r\nbooktitle = {International Conference on Artificial Intelligence and Statistics},<br \/>\r\npages = {1004\u20131012},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('193','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_193\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.jmlr.org\/proceedings\/papers\/v38\/vanhoof15.pdf\" title=\"http:\/\/www.jmlr.org\/proceedings\/papers\/v38\/vanhoof15.pdf\" target=\"_blank\">http:\/\/www.jmlr.org\/proceedings\/papers\/v38\/vanhoof15.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('193','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, H.;  Hermans, T.;  Neumann, G.;  Peters, J.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('194','tp_links')\" style=\"cursor:pointer;\">Learning Robot In-Hand Manipulation with Tactile Features<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), <\/span><span class=\"tp_pub_additional_year\">2015<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_194\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('194','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_194\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('194','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_194\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{hoof2015learningrobot,<br \/>\r\ntitle = {Learning Robot In-Hand Manipulation with Tactile Features},<br \/>\r\nauthor = {H. Hoof and T. Hermans and G. Neumann and J. Peters},<br \/>\r\nurl = {http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/HoofHumanoids2015.pdf},<br \/>\r\nyear  = {2015},<br \/>\r\ndate = {2015-01-01},<br \/>\r\nbooktitle = {Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('194','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_194\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/HoofHumanoids2015.pdf\" title=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/HoofHumanoids2015.p[...]\" target=\"_blank\">http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/HoofHumanoids2015.p[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('194','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Veiga, F. F.;  Hoof, H.;  Peters, J.;  Hermans, T.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('195','tp_links')\" style=\"cursor:pointer;\">Stabilizing Novel Objects by Learning to Predict Tactile Slip<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the IEEE\/RSJ Conference on Intelligent Robots and Systems (IROS), <\/span><span class=\"tp_pub_additional_pages\">pp. 5065\u20135072, <\/span><span class=\"tp_pub_additional_year\">2015<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_195\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('195','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_195\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('195','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_195\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{veiga2015stabilizing,<br \/>\r\ntitle = {Stabilizing Novel Objects by Learning to Predict Tactile Slip},<br \/>\r\nauthor = {F. F. Veiga and H. Hoof and J. Peters and T. Hermans},<br \/>\r\nurl = {http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/IROS2015veiga.pdf},<br \/>\r\nyear  = {2015},<br \/>\r\ndate = {2015-01-01},<br \/>\r\nbooktitle = {Proceedings of the IEEE\/RSJ Conference on Intelligent Robots and Systems (IROS)},<br \/>\r\npages = {5065\u20135072},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('195','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_195\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/IROS2015veiga.pdf\" title=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/IROS2015veiga.pdf\" target=\"_blank\">http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/IROS2015veiga.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('195','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Kroemer, O.;  Daniel, C.;  Neumann, G;  Hoof, H.;  Peters, J.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('196','tp_links')\" style=\"cursor:pointer;\">Towards Learning Hierarchical Skills for Multi-Phase Manipulation Tasks<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Conference on Robotics and Automation (ICRA), <\/span><span class=\"tp_pub_additional_year\">2015<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_196\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('196','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_196\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('196','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_196\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{kroemer2015towards,<br \/>\r\ntitle = {Towards Learning Hierarchical Skills for Multi-Phase Manipulation Tasks},<br \/>\r\nauthor = {O. Kroemer and C. Daniel and G Neumann and H. Hoof and J. Peters},<br \/>\r\nurl = {http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/KroemerICRA15.pdf},<br \/>\r\nyear  = {2015},<br \/>\r\ndate = {2015-01-01},<br \/>\r\nbooktitle = {Proceedings of the International Conference on Robotics and Automation (ICRA)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('196','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_196\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/KroemerICRA15.pdf\" title=\"http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/KroemerICRA15.pdf\" target=\"_blank\">http:\/\/www.ausy.tu-darmstadt.de\/uploads\/Site\/EditPublication\/KroemerICRA15.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('196','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2014\">2014<\/h3><div class=\"tp_publication tp_publication_article\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, Herke;  Kroemer, Oliver;  Peters, Jan<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('197','tp_links')\" style=\"cursor:pointer;\">Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments<\/a> <span class=\"tp_pub_type article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">IEEE Transactions on Robotics (TRo), <\/span><span class=\"tp_pub_additional_volume\">vol. 5, <\/span><span class=\"tp_pub_additional_pages\">pp. 1198-1209, <\/span><span class=\"tp_pub_additional_year\">2014<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_197\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('197','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_197\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('197','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_197\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{hoof2014probabilistic,<br \/>\r\ntitle = {Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments},<br \/>\r\nauthor = {Herke Hoof and Oliver Kroemer and Jan Peters},<br \/>\r\nurl = {https:\/\/pdfs.semanticscholar.org\/64fa\/da588258a77f87714191857c18eb940a2353.pdf},<br \/>\r\nyear  = {2014},<br \/>\r\ndate = {2014-01-01},<br \/>\r\njournal = {IEEE Transactions on Robotics (TRo)},<br \/>\r\nvolume = {5},<br \/>\r\npages = {1198-1209},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('197','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_197\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/pdfs.semanticscholar.org\/64fa\/da588258a77f87714191857c18eb940a2353.pdf\" title=\"https:\/\/pdfs.semanticscholar.org\/64fa\/da588258a77f87714191857c18eb940a2353.pdf\" target=\"_blank\">https:\/\/pdfs.semanticscholar.org\/64fa\/da588258a77f87714191857c18eb940a2353.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('197','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Kroemer, O.;  Hoof, H.;  Neumann, G.;  Peters, J.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('198','tp_links')\" style=\"cursor:pointer;\">Learning to Predict Phases of Manipulation Tasks as Hidden States<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA), <\/span><span class=\"tp_pub_additional_year\">2014<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_198\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('198','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_198\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('198','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_198\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{kroemer2014learning,<br \/>\r\ntitle = {Learning to Predict Phases of Manipulation Tasks as Hidden States},<br \/>\r\nauthor = {O. Kroemer and H. Hoof and G. Neumann and J. Peters},<br \/>\r\nurl = {http:\/\/www.ias.informatik.tu-darmstadt.de\/publications\/Kroemer_ICRA_2014.pdf},<br \/>\r\nyear  = {2014},<br \/>\r\ndate = {2014-01-01},<br \/>\r\nbooktitle = {Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('198','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_198\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ias.informatik.tu-darmstadt.de\/publications\/Kroemer_ICRA_2014.pdf\" title=\"http:\/\/www.ias.informatik.tu-darmstadt.de\/publications\/Kroemer_ICRA_2014.pdf\" target=\"_blank\">http:\/\/www.ias.informatik.tu-darmstadt.de\/publications\/Kroemer_ICRA_2014.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('198','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Bischoff, B.;  Nguyen-Tuong, D.;  Hoof, H.;  McHutchon, A.;  Rasmussen, C. E.;  Knoll, A.;  Peters, J.;  Deisenroth, M. P.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('199','tp_links')\" style=\"cursor:pointer;\">Policy Search For Learning Robot Control Using Sparse Data<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA), <\/span><span class=\"tp_pub_additional_year\">2014<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_199\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('199','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_199\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('199','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_199\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{bischoff2014policy,<br \/>\r\ntitle = {Policy Search For Learning Robot Control Using Sparse Data},<br \/>\r\nauthor = {B. Bischoff and D. Nguyen-Tuong and H. Hoof and A. McHutchon and C. E. Rasmussen and A. Knoll and J. Peters and M. P. Deisenroth},<br \/>\r\nurl = {http:\/\/www.ias.tu-darmstadt.de\/uploads\/Publications\/Bischoff_ICRA_2014.pdf},<br \/>\r\nyear  = {2014},<br \/>\r\ndate = {2014-01-01},<br \/>\r\nbooktitle = {Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('199','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_199\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ias.tu-darmstadt.de\/uploads\/Publications\/Bischoff_ICRA_2014.pdf\" title=\"http:\/\/www.ias.tu-darmstadt.de\/uploads\/Publications\/Bischoff_ICRA_2014.pdf\" target=\"_blank\">http:\/\/www.ias.tu-darmstadt.de\/uploads\/Publications\/Bischoff_ICRA_2014.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('199','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2013\">2013<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, H.;  Kroemer, O;  Peters, J.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('200','tp_links')\" style=\"cursor:pointer;\">Probabilistic Interactive Segmentation for Anthropomorphic Robots in Cluttered Environments<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), <\/span><span class=\"tp_pub_additional_year\">2013<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_200\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('200','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_200\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('200','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_200\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{hoof2013probabilistic,<br \/>\r\ntitle = {Probabilistic Interactive Segmentation for Anthropomorphic Robots in Cluttered Environments},<br \/>\r\nauthor = {H. Hoof and O Kroemer and J. Peters},<br \/>\r\nurl = {http:\/\/www.ias.informatik.tu-darmstadt.de\/uploads\/Publications\/hoof-HUMANOIDS.pdf},<br \/>\r\nyear  = {2013},<br \/>\r\ndate = {2013-01-01},<br \/>\r\nbooktitle = {Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('200','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_200\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ias.informatik.tu-darmstadt.de\/uploads\/Publications\/hoof-HUMANOIDS.pdf\" title=\"http:\/\/www.ias.informatik.tu-darmstadt.de\/uploads\/Publications\/hoof-HUMANOIDS.pd[...]\" target=\"_blank\">http:\/\/www.ias.informatik.tu-darmstadt.de\/uploads\/Publications\/hoof-HUMANOIDS.pd[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('200','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2012\">2012<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, H.;  Kroemer, O.;  Amor, H. Ben;  Peters, J.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('201','tp_links')\" style=\"cursor:pointer;\">Maximally Informative Interaction Learning for Scene Exploration<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Conference on Robot Systems (IROS), <\/span><span class=\"tp_pub_additional_year\">2012<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_201\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('201','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_201\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('201','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_201\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{hoof2012maximally,<br \/>\r\ntitle = {Maximally Informative Interaction Learning for Scene Exploration},<br \/>\r\nauthor = {H. Hoof and O. Kroemer and H. Ben Amor and J. Peters},<br \/>\r\nurl = {http:\/\/www.ias.informatik.tu-darmstadt.de\/uploads\/Publications\/VanHoof_IROS_2012.pdf},<br \/>\r\nyear  = {2012},<br \/>\r\ndate = {2012-01-01},<br \/>\r\nbooktitle = {Proceedings of the International Conference on Robot Systems (IROS)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('201','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_201\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.ias.informatik.tu-darmstadt.de\/uploads\/Publications\/VanHoof_IROS_2012.pdf\" title=\"http:\/\/www.ias.informatik.tu-darmstadt.de\/uploads\/Publications\/VanHoof_IROS_2012[...]\" target=\"_blank\">http:\/\/www.ias.informatik.tu-darmstadt.de\/uploads\/Publications\/VanHoof_IROS_2012[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('201','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2011\">2011<\/h3><div class=\"tp_publication tp_publication_inproceedings\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, H.;  Zant, T.;  Wiering, M. A.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('202','tp_links')\" style=\"cursor:pointer;\">Adaptive Visual Face Tracking for an Autonomous Robot<\/a> <span class=\"tp_pub_type inproceedings\">Proceedings Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_booktitle\">Proceedings of the Belgian-Dutch Artificial Intelligence Conference (BNAIC 11), <\/span><span class=\"tp_pub_additional_year\">2011<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_202\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('202','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_202\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('202','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_202\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@inproceedings{hoof2011adaptive,<br \/>\r\ntitle = {Adaptive Visual Face Tracking for an Autonomous Robot},<br \/>\r\nauthor = {H. Hoof and T. Zant and M. A. Wiering},<br \/>\r\nurl = {http:\/\/robot-learning.de\/uploads\/Publications\/VanHoof_BNAIC_2011.pdf},<br \/>\r\nyear  = {2011},<br \/>\r\ndate = {2011-01-01},<br \/>\r\nbooktitle = {Proceedings of the Belgian-Dutch Artificial Intelligence Conference (BNAIC 11)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {inproceedings}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('202','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_202\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/robot-learning.de\/uploads\/Publications\/VanHoof_BNAIC_2011.pdf\" title=\"http:\/\/robot-learning.de\/uploads\/Publications\/VanHoof_BNAIC_2011.pdf\" target=\"_blank\">http:\/\/robot-learning.de\/uploads\/Publications\/VanHoof_BNAIC_2011.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('202','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><\/div><\/div>\n<h2>Ph.D. Thesis<\/h2>\n<div class=\"teachpress_pub_list\"><form name=\"tppublistform\" method=\"get\"><a name=\"tppubs\" id=\"tppubs\"><\/a><\/form><div class=\"teachpress_publication_list\"><h3 class=\"tp_h3\" id=\"tp_h3_2016\">2016<\/h3><div class=\"tp_publication tp_publication_phdthesis\"><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Hoof, H.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('191','tp_links')\" style=\"cursor:pointer;\">Machine Learning through Exploration for Perception-Driven Robotics<\/a> <span class=\"tp_pub_type phdthesis\">PhD Thesis<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_year\">2016<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_191\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('191','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_191\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('191','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_191\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@phdthesis{hoof2016,<br \/>\r\ntitle = {Machine Learning through Exploration for Perception-Driven Robotics},<br \/>\r\nauthor = {H. Hoof},<br \/>\r\nurl = {https:\/\/tuprints.ulb.tu-darmstadt.de\/5749\/1\/thesis_front.pdf},<br \/>\r\nyear  = {2016},<br \/>\r\ndate = {2016-01-01},<br \/>\r\nbooktitle = {PhD Thesis},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {phdthesis}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('191','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_191\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-file-pdf\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/tuprints.ulb.tu-darmstadt.de\/5749\/1\/thesis_front.pdf\" title=\"https:\/\/tuprints.ulb.tu-darmstadt.de\/5749\/1\/thesis_front.pdf\" target=\"_blank\">https:\/\/tuprints.ulb.tu-darmstadt.de\/5749\/1\/thesis_front.pdf<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('191','tp_links')\">Close<\/a><\/p><\/div><\/div><\/div><\/div><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Conference and journal papers Ph.D. Thesis<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"_links":{"self":[{"href":"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/homepage\/index.php?rest_route=\/wp\/v2\/pages\/46"}],"collection":[{"href":"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/homepage\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/homepage\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/homepage\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/homepage\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=46"}],"version-history":[{"count":0,"href":"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/homepage\/index.php?rest_route=\/wp\/v2\/pages\/46\/revisions"}],"wp:attachment":[{"href":"https:\/\/staff.fnwi.uva.nl\/h.c.vanhoof\/homepage\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=46"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}