Scalable Planning and Learning for Multiagent POMDPs

Amato, Christopher and Oliehoek, Frans A ORCID: 0000-0003-4372-5055 (2015) Scalable Planning and Learning for Multiagent POMDPs. In: 2015.

Text Amato15AAAI.pdf - Unspecified Download (899kB)

Abstract

<jats:p> 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. </jats:p>

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	POMDPs, Multiagent POMDPs, Reinforcement Learning, Online Planning
Subjects:	?? QA75 ??
Depositing User:	Symplectic Admin
Date Deposited:	20 Oct 2015 07:48
Last Modified:	24 Mar 2024 19:37
DOI:	10.1609/aaai.v29i1.9439
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/2032361