The necessity for cooperation among intelligent machines has popularised cooperative multi-agent reinforcement learning (MARL) in the artificial intelligence (AI) research community. However, many research endeavors have been focused on developing practical MARL algorithms whose effectiveness has been studied only empirically, thereby lacking theoretical guarantees. As recent studies have revealed, MARL methods often achieve performance that is unstable in terms of reward monotonicity or suboptimal at convergence. To resolve these issues, in this paper, we introduce a novel framework named Heterogeneous-Agent Mirror Learning (HAML) that provides a general template for MARL algorithmic designs. We prove that algorithms derived from the HAML template satisfy the desired properties of the monotonic improvement of the joint reward and the convergence to Nash equilibrium. We verify the practicality of HAML by proving that the current state-of-the-art cooperative MARL algorithms, HATRPO and HAPPO, are in fact HAML instances. Next, as a natural outcome of our theory, we propose HAML extensions of two well-known RL algorithms, HAA2C (for A2C) and HADDPG (for DDPG), and demonstrate their effectiveness against strong baselines on StarCraftII and Multi-Agent MuJoCo tasks.

本文介绍了一种名为异构代理镜像学习（HAML）的新型框架，该框架提供了一种通用的MARL算法设计模板，解决了在奖励单调性或收敛时的非最优性能问题，通过证明来自HAML模板的算法满足单调改进联合奖励和收敛到纳什均衡的期望属性，并通过在星际争霸II和多智能体MuJoCo任务中验证了HAML的实用性。

异质代理镜像学习：协作多智能体强化学习的一系列解决方案