Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning

Huizhen Yu, Yi Wan 0004, Richard S. Sutton. Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning. SIAM J. Control and Optimization, 64(3):1456-1481, 2026. [doi]

Abstract

Abstract is missing.