A fundamental challenge in multi-agent reinforcement learning (MARL) is to learn the joint policy in an extremely large search space, which grows exponentially with the number of agents. Moreover, fully decentralized policy factorization significantly restricts the search space, which may lead to sub-optimal policies. In contrast, the auto-regressive joint policy can represent a much richer class of joint policies by factorizing the joint policy into the product of a series of conditional individual policies. While such factorization introduces the action dependency among agents explicitly in sequential execution, it does not take full advantage of the dependency during learning. In particular, the subsequent agents do not give the preceding agents feedback about their decisions. In this paper, we propose a new framework Back-Propagation Through Agents (BPTA) that directly accounts for both agents' own policy updates and the learning of their dependent counterparts. This is achieved by propagating the feedback through action chains. With the proposed framework, our Bidirectional Proximal Policy Optimisation (BPPO) outperforms the state-of-the-art methods. Extensive experiments on matrix games, StarCraftII v2, Multi-agent MuJoCo, and Google Research Football demonstrate the effectiveness of the proposed method.

翻译：多智能体强化学习（MARL）的一个基本挑战是在规模随智能体数量呈指数增长的极端庞大搜索空间中学习联合策略。此外，完全去中心化的策略分解显著限制了搜索空间，可能导致策略陷入次优。相比之下，自回归联合策略通过将联合策略分解为一系列条件化个体策略的乘积，能够表征更丰富的联合策略类别。尽管这种分解在顺序执行过程中显式引入了智能体间的动作依赖关系，但在学习过程中并未充分利用该依赖关系——后续智能体并未向前置智能体反馈其决策信息。本文提出一种名为“通过智能体的反向传播”（BPTA）的新框架，该框架直接统筹考虑智能体自身的策略更新及其依赖对应智能体的学习过程，通过沿动作链传播反馈信息实现这一目标。基于所提框架，我们提出的双向近端策略优化（BPPO）方法超越了现有最优方法。在矩阵博弈、星际争霸II v2、多智能体MuJoCo及谷歌研究足球上的大量实验验证了该方法的有效性。