Emerging reinforcement learning (RL) applications necessitate the design of sample-efficient solutions in order to accommodate the explosive growth of problem dimensionality. Despite the empirical success, however, our understanding about the statistical limits of RL remains highly incomplete. In this talk, I will present some recent progress towards settling the sample complexity in two RL scenarios. The first one is concerned with offline or batch RL, which performs learning using only pre-collected data without further exploration. We prove that model-based offline RL --- a plug-in approach that leverages the pessimism principle with Bernstein-style penalty --- achieves minimal-optimal sample complexity without any burn-in cost. The second scenario is concerned with multi-agent RL in zero-sum Markov games, assuming access to a generative model (a.k.a. simulator). We develop a new algorithm --- built upon the integration of adaptive sampling, online learning, and the optimism principle --- that overcomes the curse of multi-agents and the barrier of long horizon simultaneously.  Our results emphasize the prolific interplay between high-dimensional statistics, online learning, and game theory. (See https://arxiv.org/abs/2204.05275 and https://arxiv.org/abs/2208.10458 for more details).




This is based on joint work with Gen Li, Laixi Shi, Yuling Yan, Yuejie Chi, Jianqing Fan, and Yuting Wei.

12月7日
10:30am - 11:30am
地点
https://hkust.zoom.us/j/95008648547 (Passcode: hkust)
讲者/表演者
Prof. Yuxin CHEN
University of Pennsylvania
主办单位
Department of Mathematics
联系方法
付款详情
对象
Alumni, Faculty and staff, PG students, UG students
语言
英语
其他活动
5月24日
研讨会, 演讲, 讲座
IAS / School of Science Joint Lecture - Confinement Controlled Electrochemistry: Nanopore beyond Sequencing
Abstract Nanopore electrochemistry refers to the promising measurement science based on elaborate pore structures, which offers a well-defined geometric confined space to adopt and characterize sin...
5月13日
研讨会, 演讲, 讲座
IAS / School of Science Joint Lecture – Expanding the Borders of Chemical Reactivity
Abstract The lecture will demonstrate how it has been possible to expand the borders of cycloadditions beyond the “classical types of cycloadditions” applying organocatalytic activation principles....