Regret Bounds for Risk-Sensitive Reinforcement LearningDownload PDF

Published: 31 Oct 2022, 18:00, Last Modified: 11 Oct 2022, 16:48NeurIPS 2022 AcceptReaders: Everyone
Keywords: Risk-sensitive reinforcement learning, CVaR objective
TL;DR: We prove the first regret bounds for reinforcement learning under a general class of risk-sensitive objectives including the popular CVaR objective.
Abstract: In safety-critical applications of reinforcement learning such as healthcare and robotics, it is often desirable to optimize risk-sensitive objectives that account for tail outcomes rather than expected reward. We prove the first regret bounds for reinforcement learning under a general class of risk-sensitive objectives including the popular CVaR objective. Our theory is based on a novel characterization of the CVaR objective as well as a novel optimistic MDP construction.
Supplementary Material: pdf
16 Replies

Loading