MACb.2

Achieving the Minimax Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach

Yue Wang, University of Central Florida, United States; Jinjun Xiong, Shaofeng Zou, University at Buffalo, United States
Session:
MACb: Sequential Methods and Reinforcement Learning Lecture
Track:
Adaptive Systems, Machine Learning, and Data Analytics
Location:
Chapel
Presentation Time:
Mon, 28 Oct, 10:40 - 11:05 PT (UTC -8)
Session Chair:
Yao Xie, Georgia Institute of Technology
Presentation
Discussion
Resources
No resources available.
Session MACb
MACb.1: Modular Analysis of Change Detection Based Algorithms for Piecewise Stationary Bandits
Yu-Han Huang, Argyrios Gerogiannis, Subhonmesh Bose, Venugopal Veeravalli, University of Illinois at Urbana-Champaign, United States
MACb.2: Achieving the Minimax Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach
Yue Wang, University of Central Florida, United States; Jinjun Xiong, Shaofeng Zou, University at Buffalo, United States
MACb.3: Sinkhorn Distributionally Robust Optimization
Jie Wang, Georgia Institute of Technology, United States; Rui Gao, University of Texas at Austin, United States; Yao Xie, Georgia Institute of Technology, United States
MACb.4: Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty
Laixi Shi, Eric Mazumdar, California Institute of Technology, United States; Yuejie Chi, Carnegie Mellon University, United States; Adam Wierman, California Institute of Technology, United States
Contacts