As part of consortium of 8 European countries, I will be involved in AI4REALNET (AI for real-world network operations). In this project, we will investigate how AI can be used to support decision making by human operators to improve safety and efficiency in the energy and transport sectors. AI4REALNET receives funding from the European Union’s Horizon Europe Research and Innovation programme.
2-day graduate course on “adaptive hybrid intelligence”
We are organizing a course for PhD students in the Netherlands around training RL agents to assist or collaborate with people. I’m very happy with our line-up. Read more!
Postdoc positions on AI for sustainable molecules and materials
The university of Amsterdam is looking for 4 postdocs on the topic of AI for meta-materials. One of the positions will be co-advised by me, on the topic of “Machine Learning-based models of plant protein mixtures for sustainable food design”. Two other positions are co-advised by AMLab colleagues. Deadline for applications is 16 May. Apply is only possible through the form here.
(Note that another postdoc position at the VU on learning and reasoning for medical decision making is also still open, see below).
TMLR paper accepted
David Kuric’s paper on learning re-useable options was accepted to TMLR. Paper, code, and video are available on OpenReview. It proposes a gradient-based meta learning approach to discover sub-policies that are useful for rapid adaptation to different MDPs in a family of tasks. Congrats, David!
Postdoc position on learning an reasoning for medical decision making
At the VU Amsterdam, there are two open postdoc positions on decision making in the medical domain. In one of them, I will be involved as co-advisor. For all details and how to apply, please check the official vacancy.
ICLR paper accepted
Qi and Marco’s paper got accept for presentation at ICLR. Congratulations! The submitted version is available here, camera-ready version is coming soon.
Neurips papers
This week, Qi Wang is presenting his paper on meta-learning mixture-of-expert neural processes and Mukul Gagrani and Corrado Rainone their paper on neural topological ordering for computation graphs at NeurIPS. Furthermore, Matthew Macfarlane will present preliminary work on learning tree-based policies in the Deep Reinforcement Learning workshop.
ICML paper accepted
Two IJCAI papers accepted
Two of our IJCAI submissions were accepted:
With Niklas Höpner & Ilaria Tiddi: Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods (pre-print)
With Jan Wöhlke & Felix Schmitt: Value Refinement Network (VRN) (earlier version)
Congrats Jan & Niklas!
New working paper on class abstractions in RL
Niklas Höpner has recently posted his working paper on leveraging class abstraction for commonsense reinforcement learning. It is available on the arXiv.