Towards Optimal Performance and Action Consistency Guarantees in Dec-POMDPs with Inconsistent Beliefs and Limited Communication

TL;DR

This paper introduces a decentralized framework for multi-agent decision-making under uncertainty that explicitly manages belief inconsistencies and communication limitations, providing probabilistic guarantees for performance and coordination.

Contribution

It presents a novel approach that accounts for belief inconsistencies in Dec-POMDPs, with probabilistic guarantees and selective communication strategies.

Findings

Outperforms state-of-the-art algorithms in simulations

Provides probabilistic guarantees for action consistency and performance

Effectively manages belief inconsistencies with limited communication

Abstract

Multi-agent decision-making under uncertainty is fundamental for effective and safe autonomous operation. In many real-world scenarios, each agent maintains its own belief over the environment and must plan actions accordingly. However, most existing approaches assume that all agents have identical beliefs at planning time, implying these beliefs are conditioned on the same data. Such an assumption is often impractical due to limited communication. In reality, agents frequently operate with inconsistent beliefs, which can lead to poor coordination and suboptimal, potentially unsafe, performance. In this paper, we address this critical challenge by introducing a novel decentralized framework for optimal joint action selection that explicitly accounts for belief inconsistencies. Our approach provides probabilistic guarantees for both action consistency and performance with respect to open-loop multi-agent POMDP (which assumes all data is always communicated), and selectively triggers communication only when needed. Furthermore, we address another key aspect of whether, given a chosen joint action, the agents should share data to improve expected performance in inference. Simulation results show our approach outperforms state-of-the-art algorithms.