NeurIPS 2020 Schedule

( events) Timezone:

Workshop

Sat Dec 12 09:00 AM -- 06:00 PM (PST)

Offline Reinforcement Learning

Aviral Kumar · Rishabh Agarwal · George Tucker · Lihong Li · Doina Precup · Aviral Kumar

Workshop Home Page

The common paradigm in reinforcement learning (RL) assumes that an agent frequently interacts with the environment and learns using its own collected experience. This mode of operation is prohibitive for many complex real-world problems, where repeatedly collecting diverse data is expensive (e.g., robotics or educational agents) and/or dangerous (e.g., healthcare). Alternatively, Offline RL focuses on training agents with logged data in an offline fashion with no further environment interaction. Offline RL promises to bring forward a data-driven RL paradigm and carries the potential to scale up end-to-end learning approaches to real-world decision making tasks such as robotics, recommendation systems, dialogue generation, autonomous driving, healthcare systems and safety-critical applications. Recently, successful deep RL algorithms have been adapted to the offline RL setting and demonstrated a potential for success in a number of domains, however, significant algorithmic and practical challenges remain to be addressed. The goal of this workshop is to bring attention to offline RL, both from within and from outside the RL community discuss algorithmic challenges that need to be addressed, discuss potential real-world applications, discuss limitations and challenges, and come up with concrete problem statements and evaluation protocols, inspired from real-world applications, for the research community to work on.

For details on submission please visit: https://offline-rl-neurips.github.io/ (Submission deadline: October 9, 11:59 pm PT)

Speakers:
Emma Brunskill (Stanford)
Finale Doshi-Velez (Harvard)
John Langford (Microsoft Research)
Nan Jiang (UIUC)
Brandyn White (Waymo Research)
Nando de Freitas (DeepMind)


	Introduction


	Offline RL (Talk)


	Q&A w/ Nando de Freitas (Q&A)


	Contributed Talk 1: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs (Talk)


	Contributed Talk 2: Chaining Behaviors from Data with Model-Free Reinforcement Learning (Talk)


	Contributed Talk 3: Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets (Talk)


	Contributed Talk 4: Addressing Extrapolation Error in Deep Offline Reinforcement Learning (Talk)


	Q/A for Contributed Talks 1 (Q/A)


	Poster Session 1 (gather.town) (Poster Session)


	Causal Structure Discovery in RL (Talk)


	Q&A w/ John Langford (Q&A)


	Panel


	Learning a Multi-Agent Simulator from Offline Demonstrations (Talk)


	Q&A w/ Brandyn White (Q&A)


	Towards Reliable Validation and Evaluation for Offline RL (Talk)


	Q&A w/ Nan Jiang (Q&A)


	Contributed Talk 5: Latent Action Space for Offline Reinforcement Learning (Talk)


	Contributed Talk 6: What are the Statistical Limits for Batch RL with Linear Function Approximation? (Talk)


	Contributed Talk 7: Distilled Thompson Sampling: Practical and Efficient Thompson Sampling via Imitation Learning (Talk)


	Contributed Talk 8: Batch-Constrained Distributional Reinforcement Learning for Session-based Recommendation (Talk)


	Q/A for Contributed Talks 2 (Q&A)


	Poster Session 2 (gather.town) (Poster Session)


	Counterfactuals and Offline RL (Talk)


	Q&A w/ Emma Brunskill (Q&A)


	Batch RL Models Built for Validation (Talk)


	Q&A w/ Finale Doshi-Velez (Q&A)


	Closing Remarks