Publications

@inproceedings{huang2024going,

title = {Going Beyond Popularity and Positivity Bias: Correcting for Multifactorial Bias in Recommender Systems},

author = {Huang, Jin and Oosterhuis, Harrie and Mansoury, Masoud and van Hoof, Herke and de Rijke, Maarten},

year  = {2024},

date = {2024-07-14},

urldate = {2024-07-14},

booktitle = {International ACM SIGIR Conference on Research and Development in Information Retrieval},

keywords = {},

pubstate = {forthcoming},

tppubtype = {inproceedings}

}

@inproceedings{kuric2024planning,

title = {Planning with a Learned Policy Basis to Optimally Solve Complex Tasks},

author = {Kuric, D. and Infante, G. and Gómez, V. and Jonsson, A. and van Hoof, H. },

url = {https://openreview.net/forum?id=6N1uCtBhcL},

year  = {2024},

date = {2024-06-01},

booktitle = {International Conference on Automated Planning and Scheduling},

keywords = {},

pubstate = {forthcoming},

tppubtype = {inproceedings}

}

@inproceedings{loftin2024uncoupled,

title = {Uncoupled Learning of Differential Stackelberg Equilibria with Commitments},

author = {Loftin, Robert and Çelikok, Mustafa Mert and van Hoof, Herke and Kaski, Samuel and Oliehoek, Frans},

url = {https://arxiv.org/abs/2302.03438},

year  = {2024},

date = {2024-05-06},

urldate = {2024-05-06},

booktitle = {Artificial Agents and Multi-Agent Systems (AAMAS)},

keywords = {},

pubstate = {forthcoming},

tppubtype = {inproceedings}

}

@inproceedings{learning2023woehlke,

title = {Learning Hierarchical Planning-Based Policies from Offline Data},

author = {Woehlke, J. and Schmitt, F. and van Hoof, H. },

year  = {2023},

date = {2023-09-18},

booktitle = {Machine Learning and Knowledge Discovery in Databases: Research Track (ECML PKDD)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bakker2023learning,

title = { Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes},

author = {Bakker, T. and van Hoof, H. and Welling, M. },

year  = {2023},

date = {2023-09-17},

urldate = {2023-09-17},

booktitle = {Machine Learning and Knowledge Discovery in Databases: Research Track (ECML PKDD)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wang2023bridge,

title = {Bridge the Inference Gaps of Neural Processes via Expectation Maximization},

author = {Qi Wang and Marco Federici and Herke Hoof},

url = {https://openreview.net/forum?id=A7v2DqLjZdq},

year  = {2023},

date = {2023-05-01},

urldate = {2023-05-01},

booktitle = {International Conference on Learning Representations},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wang2022learning,

title = {Learning Expressive Meta-Representations with Mixture of Expert Neural Processes},

author = {Qi Wang and Herke Hoof},

url = {https://openreview.net/forum?id=ju38DG3sbg6},

year  = {2022},

date = {2022-11-29},

booktitle = {Advances in Neural Information Processing Systems},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gagrani2022neural,

title = {Neural Topological Ordering for Computation Graphs},

author = {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},

url = {https://arxiv.org/abs/2207.05899},

year  = {2022},

date = {2022-11-29},

booktitle = {Advances in Neural Information Processing Systems},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wohlke2022value,

title = {Value Refinement Network (VRN)},

author = {Jan Wöhlke and Felix Schmitt and Herke Hoof},

url = {https://www.ijcai.org/proceedings/2022/494},

year  = {2022},

date = {2022-07-23},

booktitle = {International Joint Conference on Artificial Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hopner2022leveraging,

title = {Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods},

author = {Niklas Höpner and Ilaria Tiddi and Herke Hoof},

url = {https://arxiv.org/abs/2201.12126},

year  = {2022},

date = {2022-07-23},

urldate = {2022-07-23},

booktitle = {International Joint Conference on Artificial Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{giri2022logic,

title = {Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine},

author = {Charul Giri and Ole-Christopher Granmo and Herke Hoof and Christian D. Blakely},

url = {https://arxiv.org/abs/2203.04378},

year  = {2022},

date = {2022-07-18},

booktitle = {International Joint Conference on Neural Networks},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wang2022model,

title = {Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search},

author = {Qi Wang and Herke Hoof},

url = {https://drive.google.com/file/d/1M9WO4Q-8h_iJ7vAyYTQjCRJki-zYS5Mu/view},

year  = {2022},

date = {2022-07-17},

booktitle = {International Conference on Machine Learning},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kool2022deep,

title = {Deep Policy Dynamic Programming for Vehicle Routing Problems},

author = {Wouter Kool and Herke Hoof and Joaquim Gromicho and Max Welling},

url = {https://arxiv.org/abs/2102.11756},

year  = {2022},

date = {2022-06-20},

booktitle = {International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{pol2022multi,

title = {Multi-Agent MDP Homomorphic Networks},

author = {Elise Pol and Herke Hoof and Frans Oliehoek and Max Welling},

url = {https://openreview.net/forum?id=H7HDG–DJF0},

year  = {2022},

date = {2022-04-25},

booktitle = {Proceedings of the International Conference on Learning Representations},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{long2022fast,

title = {Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation},

author = {Alex Long and Alan Blair and Herke Hoof},

url = {https://arxiv.org/abs/2203.03078 

https://www.aaai.org/AAAI22Papers/AAAI-8450.LongA.pdf},

year  = {2022},

date = {2022-02-21},

booktitle = {AAAI National Conference on Artificial Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhang2021deep,

title = {Deep Coherent Exploration For Continuous Control},

author = {Yijie Zhang and Herke Hoof},

url = {http://proceedings.mlr.press/v139/zhang21t.html},

year  = {2021},

date = {2021-07-19},

booktitle = {International Conference on Machine Learning},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{woehlke2021hierarchies,

title = {Hierarchies of Planning and Reinforcement Learning for Robot Navigation},

author = {J. Wöhlke and F. Schmitt and H. Hoof},

url = {https://arxiv.org/abs/2109.11178},

year  = {2021},

date = {2021-05-30},

booktitle = {IEEE International Conference on Robotics and Automation},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{pol2020mdp,

title = {MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning},

author = {Elise Pol and Daniel Worrall and Herke Hoof and Frans Oliehoek and Max Welling},

url = {https://arxiv.org/abs/2006.16908 

https://proceedings.neurips.cc/paper/2020/hash/2be5f9c2e3620eb73c2972d7552b6cb5-Abstract.html},

year  = {2020},

date = {2020-12-02},

booktitle = {Advances in Neural Information Processing Systems},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bakker2020experimental,

title = {Experimental design for MRI by greedy policy search},

author = {Tim Bakker and Herke Hoof and Max Welling},

url = {https://arxiv.org/abs/2010.16262 

https://proceedings.neurips.cc/paper/2020/hash/daed210307f1dbc6f1dd9551408d999f-Abstract.html},

year  = {2020},

date = {2020-12-02},

booktitle = {Advances in Neural Information Processing Systems},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{huang2020keeping,

title = {Keeping Dataset Biases out of the Simulation: A Debiased Simulator for Reinforcement Learning based Recommender Systems},

author = {Jin Huang and Harrie Oosterhuis and Maarten Rijke and Herke Hoof},

url = {https://dl.acm.org/doi/10.1145/3383313.3412252 

https://staff.fnwi.uva.nl/m.derijke/wp-content/papercite-data/pdf/huang-2020-keeping.pdf},

year  = {2020},

date = {2020-09-22},

booktitle = {The ACM Conference on Recommender Systems},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{heide2020social,

title = {Social Navigation with Human Empowerment Driven Reinforcement Learning},

author = {Tessa Heide and Florian Mirus and Herke Hoof},

url = {https://arxiv.org/abs/2003.08158},

year  = {2020},

date = {2020-09-15},

booktitle = {International Conference on Artificial Neural Networks},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wang2020doubly,

title = {Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables},

author = {Qi Wang and Herke Hoof},

url = {https://proceedings.icml.cc/static/paper_files/icml/2020/2280-Paper.pdf},

year  = {2020},

date = {2020-07-12},

booktitle = {International Conference on Machine Learning},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mollinga2020autonomous,

title = {An Autonomous Free Airspace En-route Controller using Deep Reinforcement Learning Techniques},

author = {Jasper Mollinga and Herke Hoof},

url = {https://arxiv.org/abs/2007.01599},

year  = {2020},

date = {2020-06-23},

booktitle = {International Conference on Research in Air Transportation},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{woehlke2020performance,

title = {A Performance-Based Start State Curriculum Framework for Reinforcement Learning},

author = {Jan Wöhlke and Felix Schmitt and Herke Hoof},

url = {http://ifaamas.org/Proceedings/aamas2020/pdfs/p1503.pdf},

year  = {2020},

date = {2020-05-09},

booktitle = {International Conference on Autonomous Agents and Multi-Agent Systems},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kool2020estimating,

title = {Estimating Gradients for Discrete Random Variables by Sampling without Replacement},

author = {Wouter Kool and Herke Hoof and Max Welling},

url = {https://openreview.net/pdf?id=rklEj2EFvB 

https://youtu.be/KtP-Z2bvPPE},

year  = {2020},

date = {2020-04-26},

booktitle = {International Conference on Learning Representations},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{page2019deep,

title = {Deep Generative Modeling of LiDAR Data},

author = {Lucas Caccia and Herke Hoof and Aaron C. Courville and Joelle Pineau},

url = {https://arxiv.org/abs/1812.01180},

year  = {2019},

date = {2019-11-04},

booktitle = {IEEE International Conference on Intelligent Robots and Systems},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{shang2019stochastic,

title = {Stochastic Activation Actor Critic Methods},

author = {Wenling Shang and Douwe Wal and Herke Hoof and Max Welling},

url = {https://ecmlpkdd2019.org/downloads/paper/483.pdf},

year  = {2019},

date = {2019-09-16},

booktitle = {European Conference on Machine Learning},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kool2019stochastic,

title = {Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement},

author = {Wouter Kool and Herke Van Hoof and Max Welling},

url = {http://proceedings.mlr.press/v97/kool19a/kool19a.pdf 

http://proceedings.mlr.press/v97/kool19a/kool19a-supp.pdf},

year  = {2019},

date = {2019-06-10},

booktitle = {International Conference on Machine Learning},

pages = {3499–3508},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{thakur2019uncertainty,

title = {Uncertainty aware Imitation Learning on Multiple Tasks using Bayesian Neural Networks},

author = {S. Thakur and H. Hoof and J. C. Gamboa Higuera and D. Precup and D. Meger},

url = {https://arxiv.org/abs/1903.05697},

year  = {2019},

date = {2019-05-20},

booktitle = {International Conference on Robotics and Automation},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kool2019attention,

title = {Attention! Learn to solve routing problems!},

author = {Wouter Kool and Herke Hoof and Max Welling},

url = {https://openreview.net/pdf?id=ByxBFsRqYm},

year  = {2019},

date = {2019-05-06},

booktitle = {International Conference on Learning Representations},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{manjannab,

title = {Policy Search on Aggregated State Space for Active Sampling},

author = {S. Manjanna and H. Hoof and G. Dudek},

url = {http://www.cim.mcgill.ca/~mrl/pubs/sandeep/ISER2018.pdf},

year  = {2018},

date = {2018-11-05},

booktitle = {International Symposium on Experimental Robotics},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{dong2018bandit,

title = {BanditSum: Extractive Summarization as a Contextual Bandit},

author = {Y. Dong and Y. Shen and E. Crawford and H. Hoof and J. C. K. Cheung},

url = {https://arxiv.org/abs/1809.09672 

http://www.aclweb.org/anthology/D18-1409},

year  = {2018},

date = {2018-10-31},

booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)},

pages = {3739–3748},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{manjanna2018reinforcement,

title = {Reinforcement Learning with Non-uniform State Representations for Adaptive Search},

author = {S. Manjanna and H. Hoof and G. Dudek},

url = {http://www.cim.mcgill.ca/~mrl/pubs/sandeep/SSRR2018.pdf},

year  = {2018},

date = {2018-08-06},

booktitle = {IEEE International Symposium on Safety, Security, and Rescue Robotics},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{fujimoto2018addressing,

title = {Addressing function approximation error in actor-critic methods},

author = {S. Fujimoto and H. Hoof and D. Meger},

url = {http://proceedings.mlr.press/v80/fujimoto18a/fujimoto18a.pdf 

http://proceedings.mlr.press/v80/fujimoto18a/fujimoto18a-supp.pdf},

year  = {2018},

date = {2018-07-10},

booktitle = {International Conference on Machine Learning},

pages = {1587–1596},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{smith2018inference,

title = {An Inference-Based Policy Gradient Method for Learning Options},

author = {M. Smith and H. Hoof and J. Pineau},

url = {http://proceedings.mlr.press/v80/smith18a/smith18a.pdf},

year  = {2018},

date = {2018-07-10},

booktitle = {International Conference on Machine Learning},

pages = {4703-4712},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2018barbaroscomparison,

title = {Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control},

author = {V. Barbaros and H. Hoof and A. Abdolmaleki and D. Meger},

url = {https://staff.fnwi.uva.nl/h.c.vanhoof/homepage/wp-content/uploads/2021/04/learningcontrol-1.pdf},

year  = {2018},

date = {2018-05-21},

booktitle = {International Conference on Robotics and Automation},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tangkaratt2017policy,

title = {Policy Search with High-Dimensional Context Variables},

author = {V. Tangkaratt and H. Hoof and S. Parisi and G. Neumann and J. Peters and M. Sugiyama},

url = {http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/tangkaratt2017policy.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},

pages = {2632–2638},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hoof2016stable,

title = {Stable Reinforcement Learning with Auto-Encoders for Tactile and Visual Data},

author = {Herke Hoof and Nutan Chen and Maximilian Karl and Patrick Smart and Jan Peters},

url = {https://www.researchgate.net/profile/Patrick_Van_der_Smagt2/publication/305725116_Stable_Reinforcement_Learning_with_Autoencoders_for_Tactile_and_Visual_Data/links/579cfd5f08ae6a2882f2e8f1.pdf},

year  = {2016},

date = {2016-01-01},

booktitle = {International Conference on Intelligent Robots and Systems},

pages = {3928–3934},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{iros2016yi,

title = {Active Tactile Object Exploration with Gaussian Processes},

author = {Z. Yi and R. Calandra and F. Veiga and H. Hoof and T. Hermans and Y. Zhang and J. Peters},

url = {http://www.ausy.tu-darmstadt.de/uploads/Publications/Other/iros2016yi.pdf},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)},

pages = {4925–4930},

crossref = {p10958},

key = {tacman, tactile manipulation},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hoof2015learning,

title = {Learning of Non-Parametric Control Policies with High-Dimensional State Features},

author = {Herke Hoof and Jan Peters and Gerhard Neumann},

url = {http://www.jmlr.org/proceedings/papers/v38/vanhoof15.pdf},

year  = {2015},

date = {2015-01-01},

booktitle = {International Conference on Artificial Intelligence and Statistics},

pages = {1004–1012},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hoof2015learningrobot,

title = {Learning Robot In-Hand Manipulation with Tactile Features},

author = {H. Hoof and T. Hermans and G. Neumann and J. Peters},

url = {http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/HoofHumanoids2015.pdf},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{veiga2015stabilizing,

title = {Stabilizing Novel Objects by Learning to Predict Tactile Slip},

author = {F. F. Veiga and H. Hoof and J. Peters and T. Hermans},

url = {http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/IROS2015veiga.pdf},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)},

pages = {5065–5072},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kroemer2015towards,

title = {Towards Learning Hierarchical Skills for Multi-Phase Manipulation Tasks},

author = {O. Kroemer and C. Daniel and G Neumann and H. Hoof and J. Peters},

url = {http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/KroemerICRA15.pdf},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the International Conference on Robotics and Automation (ICRA)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kroemer2014learning,

title = {Learning to Predict Phases of Manipulation Tasks as Hidden States},

author = {O. Kroemer and H. Hoof and G. Neumann and J. Peters},

url = {http://www.ias.informatik.tu-darmstadt.de/publications/Kroemer_ICRA_2014.pdf},

year  = {2014},

date = {2014-01-01},

booktitle = {Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bischoff2014policy,

title = {Policy Search For Learning Robot Control Using Sparse Data},

author = {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},

url = {http://www.ias.tu-darmstadt.de/uploads/Publications/Bischoff_ICRA_2014.pdf},

year  = {2014},

date = {2014-01-01},

booktitle = {Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hoof2013probabilistic,

title = {Probabilistic Interactive Segmentation for Anthropomorphic Robots in Cluttered Environments},

author = {H. Hoof and O Kroemer and J. Peters},

url = {http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/hoof-HUMANOIDS.pdf},

year  = {2013},

date = {2013-01-01},

booktitle = {Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hoof2012maximally,

title = {Maximally Informative Interaction Learning for Scene Exploration},

author = {H. Hoof and O. Kroemer and H. Ben Amor and J. Peters},

url = {http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/VanHoof_IROS_2012.pdf},

year  = {2012},

date = {2012-01-01},

booktitle = {Proceedings of the International Conference on Robot Systems (IROS)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hoof2011adaptive,

title = {Adaptive Visual Face Tracking for an Autonomous Robot},

author = {H. Hoof and T. Zant and M. A. Wiering},

url = {http://robot-learning.de/uploads/Publications/VanHoof_BNAIC_2011.pdf},

year  = {2011},

date = {2011-01-01},

booktitle = {Proceedings of the Belgian-Dutch Artificial Intelligence Conference (BNAIC 11)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}