Offline Reinforcement Learning Workshop

Neural Information Processing Systems (NeurIPS)

December 12, 2020

@OfflineRL ยท #OFFLINERL2020

Throughout the day we will be livestreaming invited talks, contributed talks, Q/A sessions and a live panel discussion. To watch the livesteam, join the zoom link on: offline RL workshop page on neurips.cc. All times listed are in EST. Please click here for a timezone converter from EST. You can submit questions for the panelists using the form below.

Time (EST) Speaker Title Recording
11:50am - 12:00pm EST Rishabh Agarwal, Aviral Kumar, George Tucker Opening Remarks [LIVE]
12:00pm - 12:40pm EST Nando De Freitas Invited Talk: Offline RL Video
12:40pm - 1:30pm EST Aayam Shrestha, Seunghyun Lee, Avi Singh, Caglar Gulchere Contributed Talks 1:
  • Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs
  • Chaining Behaviors from Data with Model-Free Reinforcement Learning
  • Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets
  • Addressing Extrapolation Error in Deep Offline Reinforcement Learning
  • Q/A [LIVE]
  • Video 1
  • Video 2
  • Video 3
  • Video 4
    		•
    1:30pm - 2:20pm EST Poster Session 1 (gather.town)
  • Room 1
  • Room 2
    • 2:20pm - 3:00pm EST John Langford Invited Talk: Causal Structure Discovery in RL [LIVE][Slides]
    3:00pm - 4:00pm EST Emma Brunskill, Nan Jiang, Nando de Freitas, Finale Doshi-Velez, Sergey Levine, John Langford, Brandyn White Panel Discussion [LIVE]
    4:10pm - 4:50pm EST Brandyn White Invited Talk: Learning a Multi-Agent Simulator from Offline Demonstrations Video
    4:50pm - 5:30pm EST Nan Jiang Invited Talk: Towards Reliable Validation and Evaluation for Offline RL Video
    5:30pm - 6:20pm EST Wenxuan Zhou, Ruosong Wang, Samuel Dalton, Diksha Garg Contributed Talks 2:
  • Latent Action Space for Offline Reinforcement Learning
  • What are the Statistical Limits for Batch RL with Linear Function Approximation?
  • Distilled Thompson Sampling: Practical and Efficient Thompson Sampling via Imitation Learning
  • Batch-Constrained Distributional Reinforcement Learning for Session-based Recommendation
  • Q/A [LIVE]
  • Video 1
  • Video 2
  • Video 3
  • Video 4
    		•
    6:20pm - 7:30pm EST Poster Session 2 (gather.town) gather.town
  • Room 1
  • Room 2
    • 7:30pm - 8:10pm EST Emma Brunskill Invited Talk: Counterfactuals and Offline RL [LIVE]
    8:10pm - 8:50pm EST Finale Doshi-Velez Invited Talk: Batch RL Models Built for Validation Video
    8:50pm - 9:00pm EST Rishabh Agarwal, Aviral Kumar, George Tucker Closing Remarks [LIVE]