Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE). However, such expected, i.e., risk-neutral, Q value is not sufficient even with CTDE due to the randomness of rewards and the uncertainty in environments, which causes the failure of these methods to train coordinating agents incomplexenvironments. Toaddress these issues, we propose RMIX, anovelcooperativeMARL method with theConditional Value at Risk (CVaR) measure over the learned distributions of individuals' Q values. Specifically, we first learn the return distributions of individuals to analytically calculate CVaRfordecentralized execution. Then,tohandle thetemporal nature of the stochastic outcomes during executions, we propose a dynamic risk level predictorforriskleveltuning.

In general, research in distributional reinforcement learning has focused on the classical setting of a scalar reward function.

We consider the problem of learning models for risk-sensitive reinforcement learning.

Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks.