Scalable Planning and Learning for Multiagent POMDPs

Authors

  • Christopher Amato Massachusetts Institute of Technology
  • Frans Oliehoek University of Amsterdam and University of Liverpool

DOI:

https://doi.org/10.1609/aaai.v29i1.9439

Keywords:

POMDPs, Multiagent POMDPs, Reinforcement Learning, Online Planning

Abstract

Online, sample-based planning algorithms for POMDPs have shown great promise in scaling to problems with large state spaces, but they become intractable for large action and observation spaces. This is particularly problematic in multiagent POMDPs where the action and observation space grows exponentially with the number of agents. To combat this intractability, we propose a novel scalable approach based on sample-based planning and factored value functions that exploits structure present in many multiagent settings. This approach applies not only in the planning case, but also in the Bayesian reinforcement learning setting. Experimental results show that we are able to provide high quality solutions to large multiagent planning and learning problems.

Downloads

Published

2015-02-18

How to Cite

Amato, C., & Oliehoek, F. (2015). Scalable Planning and Learning for Multiagent POMDPs. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). https://doi.org/10.1609/aaai.v29i1.9439

Issue

Section

AAAI Technical Track: Multiagent Systems