Proceedings of the AAAI Conference on Artificial Intelligence · 2015 · 89 citations · 29 references
ComputingAutonomous SystemsArtificial IntelligenceMachine LearningMarkov Decision ProcessesMulti-agent SystemsPolicy LearningReinforcement LearningReinforcement Learning FoundationsAgent PlanningBayesian Reinforcement LearningFactored PomdpsHigh-dimensional State SpacesMulti-agent PlanningMultiagent PomdpsScalable Multi-agent LearningScalable Planning Algorithms
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.
29
Monte-Carlo Planning in Large POMDPs
David Silver, Joel Veness · DSpace@MIT (Massachusetts Institute of Technology) · 2010 · 856 citations · Full text
Temporal Difference Learning and TD-Gammon
G. Tesauro · ICGA Journal · 1995 · 769 citations · Full text
Online Planning Algorithms for POMDPs
Stéphane Ross, Joëlle Pineau, S. Paquet et al. · Journal of Artificial Intelligence Research · 2008 · 515 citations · Full text
Multiagent Planning with Factored MDPs
Carlos Guestrin, Daphne Koller, Ronald Parr · 2001 · 403 citations