Decentralized model-free reinforcement learning in stochastic games with average-reward objective

no code implementations • 13 Jan 2023 • Romain Cravic, Nicolas Gast, Bruno Gaujal

We propose the first model-free algorithm that achieves low regret performance for decentralized learning in two-player zero-sum tabular stochastic games with infinite-horizon average-reward objective.

Q-Learning reinforcement-learning +1