Timezone: »

 
Poster
Regret Bounds for Risk-Sensitive Reinforcement Learning
Osbert Bastani · Jason Yecheng Ma · Estelle Shen · Wanqiao Xu

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #720
in Poster Session 4 »

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.

Keywords: Risk-sensitive reinforcement learning · CVaR objective
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Osbert Bastani (University of Pennsylvania)
Jason Yecheng Ma (University of Pennsylvania)
Estelle Shen (University of Pennsylvania)
Wanqiao Xu (Stanford University)

More from the Same Authors