Web: http://arxiv.org/abs/2205.05138

May 12, 2022, 1:11 a.m. | Ido Greenberg, Yinlam Chow, Mohammad Ghavamzadeh, Shie Mannor

cs.LG updates on arXiv.org arxiv.org

In risk-averse reinforcement learning (RL), the goal is to optimize some risk
measure of the returns. A risk measure often focuses on the worst returns out
of the agent's experience. As a result, standard methods for risk-averse RL
often ignore high-return strategies. We prove that under certain conditions
this inevitably leads to a local-optimum barrier, and propose a soft risk
mechanism to bypass it. We also devise a novel Cross Entropy module for risk
sampling, which (1) preserves risk aversion …

arxiv learning reinforcement reinforcement learning risk

More from arxiv.org / cs.LG updates on arXiv.org

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC

Senior Data Science Writer

@ NannyML | Remote

Director of AI/ML Engineering

@ Armis Industries | Remote (US only), St. Louis, California

Digital Analytics Manager

@ Patagonia | Ventura, California