Technical Program

Note: All times are in Pacific Daylight Time (UTC -7)

D-6: Statistical Aspects of Reinforcement Learning (invited)

Session Type: Virtual
Time: Monday, October 31, 11:00 - 12:00
Location: Virtual J
Virtual Session: Attend on Virtual Platform
 
D-6.1: Near-optimal algorithms for Imitation Learning
         Nived Rajaraman; UC Berkeley
         Jiantao Jiao; UC Berkeley
 
D-6.2: Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
         Yuting Wei; University of Pennsylvania