CPAIOR paper accepted

Wouter Kool’s paper “Deep policy dynamic programming for vehicle routing problems” was accepted to CPAIOR. Congratulations! A preprint is available on the arXiv.

AAAI paper accepted

Alex Long’s AAAI submission on Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation got accepted for presentation! The paper is the result of a collaboration started when Alex visited us at UvA. Congrats, Alex!

Several working papers posted

We’ve recently posted several working papers that I hope you’ll find interesting:

  • Amin, S., Gomrokchi, M., Satija, H., van Hoof, H., & Precup, D. (2021). A Survey of Exploration Methods in Reinforcement Learning. arXiv preprint arXiv:2109.00157.
  • Kool, W., van Hoof, H., Gromicho, J., & Welling, M. (2021). Deep Policy Dynamic Programming for Vehicle Routing Problems. arXiv preprint arXiv:2102.11756.

New publications

Jan Woehlke’s paper “Hierarchies of Planning and Reinforcement Learning for Robot Navigation” was accepted for presentation at the International Conference on Robotics and Automation.

Yijie Zhang got his paper “Deep Coherent Exploration For Continuous Control” accepted for presentation in the International Conference on Machine Learning.

Congrats Yijie & Jan! Links to the papers / preprint will follow soon on the publication page.

Open position for postdoctoral researcher

Update: Position has closed. Any jobs in our institute will be advertised here.

We are currently looking for a postdoctoral researcher for a collaboration on reinforcement learning with structured data. The position is offered as part of a collaboration with Elsevier and several other labs in Amsterdam. The collaboration will focus on fundamental research. More details can be found in the vacancy portal. Also please use the portal to submit your application if interested. Feel free to share the vacancy with anyone that might be interested.

Tim’s and Elise’s NeurIPS papers accepted

Two of our submissions to NeurIPS were accepted. Elise’s work on MDP homomorphic networks focuses on exploiting symmetries in the state-action space, and is already available as preprint here. Tim’s work focuses on the use of policy search strategies to optimize MRI acquisition strategies. Congrats, Tim and Elise!

Jin’s RecSys paper accepted

Jin Huang got a paper accepted into RecSys 2020. Her paper focuses on learning a debiased simulator from a biased data to train recommender agents using reinforcement learning. Congrats Jin!