Backpropagation Through Agents

Zhiyuan Li, Wenshuai Zhao, Lijun Wu, Joni Pajarinen

Research output: Contribution to journalConference articleScientificpeer-review


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, Multiagent MuJoCo, and Google Research Football demonstrate the effectiveness of the proposed method.

Original languageEnglish
Pages (from-to)13718-13726
Number of pages9
JournalProceedings of the AAAI Conference on Artificial Intelligence
Issue number12
Publication statusPublished - 25 Mar 2024
MoE publication typeA4 Conference publication
EventAAAI Conference on Artificial Intelligence - Vancouver, Canada
Duration: 20 Feb 202427 Feb 2024
Conference number: 38


Dive into the research topics of 'Backpropagation Through Agents'. Together they form a unique fingerprint.

Cite this