
RiskQ proposes a novel approach for risk-sensitive multi-agent reinforcement learning value factorization, satisfying the RIGM principle for common risk metrics.


coremsg

riskq-risk-sensitive-multi-agent-reinforcement-learning-value-factorization


RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization


title_rewrite


The core message of this paper is that a naive definition of regret in risk-sensitive multi-agent reinforcement learning can lead to equilibrium bias, where the most risk-sensitive agents are favored at the expense of the other agents. The authors propose a new notion of risk-balanced regret to address this issue.


analyzing-equilibrium-bias-in-risk-sensitive-multi-agent-reinforcement-learning


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