Taming Equilibrium Bias in Risk-Sensitive Multi-Agent Reinforcement Learning

arXiv:2405.02724v1 Announce Type: new
Abstract: We study risk-sensitive multi-agent reinforcement learning under general-sum Markov games, where agents optimize the entropic risk measure of rewards with possibly diverse risk preferences. We show that using the regret naively adapted from existing literature as a performance metric could induce policies with equilibrium bias that favor the most risk-sensitive agents and overlook the other agents. To address such deficiency of the naive regret, we propose a novel notion of regret, which we call risk-balanced …

abstract agent agents arxiv bias cs.gt cs.lg diverse equilibrium games general literature markov multi-agent performance policies reinforcement reinforcement learning risk show study sum type