Towards Optimal Performance and Action Consistency Guarantees in Dec-POMDPs with Inconsistent Beliefs and Limited Communication
This addresses coordination and safety issues in autonomous systems where agents have inconsistent beliefs, offering a practical solution for real-world applications, though it is incremental in improving existing methods.
The paper tackles the problem of multi-agent decision-making under inconsistent beliefs due to limited communication, introducing a decentralized framework that provides probabilistic guarantees for action consistency and performance, and selectively triggers communication, with simulation results showing it outperforms state-of-the-art algorithms.
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.