Factored Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) form a powerful framework for multiagent planning under uncertainty, but optimal solutions require a rigid history-based policy representation. In this paper we allow inter-agent communication which turns the problem in a centralized Multiagent POMDP (MPOMDP). We map belief distributions over state factors to an agent's local actions by exploiting structure in the joint MPOMDP policy. The key point is that when sparse dependencies between the agents' decisions exist, often the belief over its local state factors is sufficient for an agent to unequivocally identify the optimal action, and communication can be avoided. We formalize these notions by casting the problem into convex optimization form, and present experimental results illustrating the savings in communication that we can obtain.
João V Messias (Instituto Superior Técnico, 501 507 930 TU Lisbon)
Matthijs Spaan (Delft University of Technology)
Pedro U Lima (Instituto Superior Técnico, TU Lisbon)
More from the Same Authors
2022 Poster: Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems »
Miguel Suau · Jinke He · Mustafa Mert Çelikok · Matthijs Spaan · Frans Oliehoek