English

Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning

Machine Learning 2022-04-08 v6 Artificial Intelligence Machine Learning

Abstract

We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable. MVPI enjoys great flexibility in that any policy evaluation method and risk-neutral control method can be dropped in for risk-averse control off the shelf, in both on- and off-policy settings. This flexibility reduces the gap between risk-neutral control and risk-averse control and is achieved by working on a novel augmented MDP directly. We propose risk-averse TD3 as an example instantiating MVPI, which outperforms vanilla TD3 and many previous risk-averse control methods in challenging Mujoco robot simulation tasks under a risk-aware performance metric. This risk-averse TD3 is the first to introduce deterministic policies and off-policy learning into risk-averse reinforcement learning, both of which are key to the performance boost we show in Mujoco domains.

Keywords

Cite

@article{arxiv.2004.10888,
  title  = {Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning},
  author = {Shangtong Zhang and Bo Liu and Shimon Whiteson},
  journal= {arXiv preprint arXiv:2004.10888},
  year   = {2022}
}

Comments

AAAI 2021

R2 v1 2026-06-23T15:02:28.281Z