All talks listed in Pacific Time (PDT).

–
Opening Remarks
–
MOPO: Model-Based Offline Policy Optimization
Tengyu Ma (Stanford)
–
Learning from the Past Without Great Exploration
Emma Brunskill  (Stanford)
–
Offline Deep Reinforcement Learning Algorithms
Sergey Levine (UC Berkeley)
–
Break
–
Attacking the Off-Policy Problem With Duality
Ofir Nachum (Google Research)
–
Discussion: Offline Reinforcement Learning
Pablo Castro (Google)
–
Gather.town
–
Behaviour Suite for Reinforcement Learning
Ian Osband (DeepMind)
–
Learning Exploration Strategies with Meta-Reinforcement Learning
Chelsea Finn (Stanford University)
–
Temporally-Extended ε-Greedy Exploration
Will Dabney (DeepMind)
–
Break
–
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
Alekh Agarwal (Microsoft Research)
–
Discussion: Exploration
Joel Lehman (Uber)
–
Gather.town
–
Munchausen Reinforcement Learning
Matthieu Geist (Google)
–
Adaptive Approximate Policy Iteration
Nevena Lazic (DeepMind)
–
Stabilizing Q-learning with Weighted Bellman Losses
Pieter Abbeel (UC Berkeley)
–
Break
–
Generalizing the Projected Bellman Error Objective for Nonlinear Value Estimation
Martha White (University of Alberta)
–
Discussion: Optimization
Gergely Neu (UPF)
–
Gather.town
–
Language as a Scaffold for Reinforcement Learning
Jacob Andreas (MIT)
–
Invariant Prediction for Generalization in Reinforcement Learning
Clare Lyle (University of Oxford)
–
Exploiting Latent Structure and Bisimulation Metrics for Better Generalization
Amy Zhang (McGill University, Mila Institute, Facebook AI Research)
–
Break
–
Fast Reinforcement Learning With Generalized Policy Updates
Doina Precup  (McGill Univeristy & MILA / DeepMind)
–
Policy Gradients Methods, Neural Policy Classes, and Distribution Shift
Sham Kakade (University of Washington)
–
Gather.town
–
Is Safe Learning the Future of RL?
Scott Niekum (UT Austin)
–
Rigorous Uncertainty Quantification for Off-policy Evaluation in Reinforcement Learning: a Variational Approach
Qiang Liu (UT Austin)
–
CoinDICE: Off-Policy Confidence Interval Estimation via Dual Lens
Bo Dai (Google Brain)
–
Break
–
Mixed Autonomy Traffic: A Reinforcement Learning Perspective
Cathy Wu (MIT)
–
Deep Robust Reinforcement Learning and Regularization
Shie Mannor (Technion)
–
Gather.town