|
|
|
|
276
|
Wed, 8/11/2021,
1:30 PM -
3:20 PM
|
Virtual
|
|
Statistical Foundations of Reinforcement Learning — Topic-Contributed Papers
|
|
IMS, Section on Statistical Learning and Data Science, International Chinese Statistical Association
|
|
Organizer(s): Yuxin Chen, Princeton University
|
|
Chair(s): Yuxin Chen, Princeton University
|
|
1:35 PM
|
Breaking the sample size barrier in model-based reinforcement learning
Yuting Wei, Carnegie Mellon University
|
|
1:55 PM
|
Distributional Robust Batch Contextual Bandits
Zhengyuan Zhou, New York University
|
|
2:15 PM
|
Learning Good State and Action Representations via Tensor Decomposition
Anru Zhang, University of Wisconsin-Madison; Chengzhuo Ni, Princeton University; Yaqi Duan, Princeton University; Mengdi Wang, Princeton University
|
|
2:35 PM
|
Dynamic Batch Learning in High-Dimensional Sparse Linear Contextual Bandits
Zhimei Ren, Stanford University; Zhengyuan Zhou, New York University
|
|
2:55 PM
|
Is Q-Learning Minimax Optimal?
Yuejie Chi, Carnegie Mellon University
|
|
3:15 PM
|
Floor Discussion
|
