Multi-Agent Planning with Baseline Regret Minimization

Multi-Agent Planning with Baseline Regret Minimization

Feng Wu, Shlomo Zilberstein, Xiaoping Chen

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Main track. Pages 444-450. https://doi.org/10.24963/ijcai.2017/63

We propose a novel baseline regret minimization algorithm for multi-agent planning problems modeled as finite-horizon decentralized POMDPs. It guarantees to produce a policy that is provably better than or at least equivalent to the baseline policy. We also propose an iterative belief generation algorithm to effectively and efficiently minimize the baseline regret, which only requires necessary iterations to converge to the policy with minimum baseline regret. Experimental results on common benchmark problems confirm its advantage comparing to the state-of-the-art approaches.
Keywords:
Agent-based and Multi-agent Systems: Coordination and cooperation
Planning and Scheduling: Planning under Uncertainty
Agent-based and Multi-agent Systems: Multi-agent Planning
Planning and Scheduling: Distributed/Multi-agent Planning