论文标题
PAC增强学习算法用于通用马尔可夫游戏
PAC Reinforcement Learning Algorithm for General-Sum Markov Games
论文作者
论文摘要
本文介绍了Markov Games的近似正确（PAC）多代理增强学习（MARL）算法的理论框架。本文使用延迟Q学习的想法为著名的NASH Q学习算法提供了扩展，以构建用于通用 - 马尔可夫游戏的新的PAC MARL算法。除了指导可证明的PAC MARL算法的设计外，该框架还可以检查任意MARL算法是否为PAC。比较数值结果证明了性能和鲁棒性。
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.
