CMStatistics 2022: Start Registration
View Submission - CMStatistics
Title: Blessing from Experts: Super Reinforcement Learning in Confounded Environments Authors:  Jiayi Wang - The University of Texas at Dallas (United States) [presenting]
Zhengling Qi - The George Washington University (United States)
Chengchun Shi - LSE (United Kingdom)
Abstract: We introduce super reinforcement learning in the batch setting, which takes the observed action as input for enhanced policy learning. In the presence of unmeasured confounders, the recommendations from human experts recorded in the observed data allow us to recover certain unobserved information. Including this information in the policy search, the proposed super reinforcement learning will yield a super-policy that is guaranteed to outperform both the standard optimal policy and the behavior one (e.g., the experts recommendation). Furthermore, to address the issue of unmeasured confounding in finding super-policies, a number of non-parametric identification results are established. Finally, we develop two super-policy learning algorithms and derive their corresponding finite-sample regret guarantees.