All talk times are in Pacific Time. 

–
Coffee and Check-In
–
Opening Remarks
–
Optimizing Average Reward MDPs with a Generative Model
Aaron Sidford (Stanford University)
–
Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning
Lin Yang (UCLA)
–
Break
–
Discussion: Getting Organized
–
Lunch
–
Do Temporal Difference Learning Algorithms Achieve Optimal Approximation Error?
Ashwin Pananjady (Georgia Tech)
–
V-Learning—A Simple, Efficient, Decentralized Algorithm for Multiagent RL
Chi Jin (Princeton University)
–
Break
–
Discussion: General Function Approximation
–
Reception
–
Coffee and Check-In
–
A Simple Convergence Proof For Stochastic Approximation Using Converse Lyapunov Theory
Mathukumalli Vidyasagar (Indian Institute of Technology Hyderabad)
–
Can We Zap Optimal Transport?
Sean Meyn (University of Florida)
–
Break
–
Discussion: Failures of RL
–
Lunch
–
Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic
Zhuoran Yang (Princeton University)
–
Asymptotically Optimal Causal Effect Identification
Alan Malek (DeepMind)
–
Break
–
Discussion: Deep RL
–
Coffee and Check-In
–
Online Model Selection: Algorithms And Fundamental Limits
Vidya Muthukumar (Georgia Tech)
–
A/B/n Testing with Control in the Presence of Subpopulations
Wouter Koolen (Centrum Wiskunde & Informatica)
–
Break
–
Discussion: Teaching RL
–
Lunch
–
Exploiting Structure In Reinforcement Learning
Christina Yu (Cornell University)
–
Nonlinear Bandits and RL
Jason Lee (Princeton University)
–
Break
–
Impromptu Talks
–
Coffee and Check-In
–
Offline Reinforcement Learning: Representations, Algorithms, And Applications
Sergey Levine (UC Berkeley)
–
Provable Model-Based Nonlinear Bandit And Reinforcement Learning
Tengyu Ma (Stanford University)
–
Break
–
Discussion: Practice vs. Theory
–
Lunch
–
Off-Policy Evaluation In Partially Observed Markov Decision Processes
Stefan Wager (Stanford University)
–
Is Pessimism Provably Efficient For Offline Rl?
Zhaoran Wang (Northwestern University)
–
Break
–
Discussion: Structure and RL