Regularization of the policy updates for stabilizing Mean Field Games

no code implementations • 4 Apr 2023 • Talal Algumaei, Ruben Solozabal, REDA ALAMI, Hakim Hacid, Merouane Debbah, Martin Takac

This work studies non-cooperative Multi-Agent Reinforcement Learning (MARL) where multiple agents interact in the same environment and whose goal is to maximize the individual returns.

Multi-agent Reinforcement Learning reinforcement-learning