AI RESEARCH
Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation
arXiv CS.LG
•
ArXi:2603.09208v1 Announce Type: new Provably efficient and robust equilibrium computation in general-sum Marko games remains a core challenge in multi-agent reinforcement learning. Nash equilibrium is computationally intractable in general and brittle due to equilibrium multiplicity and sensitivity to approximation error. We study Risk-Sensitive Quantal Response Equilibrium (RQRE), which yields a unique, smooth solution under bounded rationality and risk sensitivity.