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 |