Reversible Markov decision processes and the Gaussian free field

作者：Venkat Anantharam · 发表于：Systems & Control Letters · 年份：2022 · DOI：10.1016/j.sysconle.2022.105382 · 被引用次数：3 · 研究领域：Game Theory and Applications、Markov Chains and Monte Carlo Methods、Reinforcement Learning in Robotics