Think How Your Teammates Think: Active Inference Can Benefit Decentralized Execution
Hao Wu, Shoucheng Song, Chang Yao, Sheng Han, Huaiyu Wan, Youfang Lin, Kai Lv

TL;DR
This paper introduces a non-communication multi-agent reinforcement learning framework that models teammates' decision processes through active inference, improving coordination without relying on communication.
Contribution
It proposes a novel local observation-based modeling approach that constructs teammate cognition via perception, belief, and action portraits, enhancing decentralized cooperation.
Findings
Outperforms existing methods on SMAC, SMACv2, MPE, and GRF benchmarks.
Effectively models teammates' decision logic without communication.
Improves coordination and collaboration in multi-agent systems.
Abstract
In multi-agent systems, explicit cognition of teammates' decision logic serves as a critical factor in facilitating coordination. Communication (i.e., ``\textit{Tell}'') can assist in the cognitive development process by information dissemination, yet it is inevitably subject to real-world constraints such as noise, latency, and attacks. Therefore, building the understanding of teammates' decisions without communication remains challenging. To address this, we propose a novel non-communication MARL framework that realizes the construction of cognition through local observation-based modeling (i.e., \textit{``Think''}). Our framework enables agents to model teammates' \textbf{active inference} process. At first, the proposed method produces three teammate portraits: perception-belief-action. Specifically, we model the teammate's decision process as follows: 1) Perception: observing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsEmbodied and Extended Cognition · Reinforcement Learning in Robotics · Explainable Artificial Intelligence (XAI)
