GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems

TL;DR

GlobeDiff introduces a diffusion-based method for inferring global states in multi-agent systems under partial observability, outperforming existing belief and communication approaches.

Contribution

The paper proposes GlobeDiff, a novel diffusion process model for global state inference that effectively handles ambiguities and improves accuracy in multi-agent systems.

Findings

GlobeDiff achieves higher accuracy in global state inference.

The method effectively bounds estimation errors in various distributions.

Experimental results show superior performance over existing methods.

Abstract

In the realm of multi-agent systems, the challenge of \emph{partial observability} is a critical barrier to effective coordination and decision-making. Existing approaches, such as belief state estimation and inter-agent communication, often fall short. Belief-based methods are limited by their focus on past experiences without fully leveraging global information, while communication methods often lack a robust model to effectively utilize the auxiliary information they provide. To solve this issue, we propose Global State Diffusion Algorithm~(GlobeDiff) to infer the global state based on the local observations. By formulating the state inference process as a multi-modal diffusion process, GlobeDiff overcomes ambiguities in state estimation while simultaneously inferring the global state with high fidelity. We prove that the estimation error of GlobeDiff under both unimodal and multi-modal distributions can be bounded. Extensive experimental results demonstrate that GlobeDiff achieves superior performance and is capable of accurately inferring the global state.