Decentralized partially observable Markov decision processes (Dec-POMDPs) constitute an expressive framework for multiagent planning under uncertainty, but solving them is provabl...
Frans A. Oliehoek, Matthijs T. J. Spaan, Shimon Wh...
Bayesian games can be used to model single-shot decision problems in which agents only possess incomplete information about other agents, and hence are important for multiagent co...
Frans A. Oliehoek, Matthijs T. J. Spaan, Jilles St...
Planning in single-agent models like MDPs and POMDPs can be carried out by resorting to Q-value functions: a (near-) optimal Q-value function is computed in a recursive manner by ...
Many problems of multiagent planning under uncertainty require distributed reasoning with continuous resources and resource limits. Decentralized Markov Decision Problems (Dec-MDP...
Recent scaling up of decentralized partially observable Markov decision process (DEC-POMDP) solvers towards realistic applications is mainly due to approximate methods. Of this fa...