This paper presents a theoretical framework for probably approximately correct (PAC) multi-agent reinforcement learning (MARL) algorithms for Markov games. The paper offers an extension to the well-known Nash Q-learning algorithm, using the idea of delayed Q-learning, in order to build a new PAC MARL algorithm for general-sum Markov games. In addition to guiding the design of a provably PAC MARL algorithm, the framework enables checking whether an arbitrary MARL algorithm is PAC. Comparative numerical results demonstrate performance and robustness.

中文翻译：

---

通用和马尔可夫博弈的PAC强化学习算法

本文提出了一个用于马尔可夫博弈的可能近似正确 (PAC) 多智能体强化学习 (MARL) 算法的理论框架。该论文对著名的 Nash Q-learning 算法进行了扩展，使用延迟 Q-learning 的思想，以构建一种新的 PAC MARL 算法，用于一般和马尔可夫博弈。除了指导可证明的 PAC MARL 算法的设计之外，该框架还可以检查任意 MARL 算法是否是 PAC。比较数值结果证明了性能和稳健性。