Abstract : In the domain of decentralized Markov decision processes, we develop the first complete and optimal algorithm that is able to extract deterministic policy vectors based on finite state controllers for a cooperative team of agents. Our algorithm applies to the discounted infinite horizon case and extends best-first search methods to the domain of decentralized control theory. We prove the optimality of our approach and give some first experimental results for two small test problems. We believe this to be an important step forward in learning and planning in stochastic multi-agent systems.
https://hal.inria.fr/inria-00000205 Contributor : Daniel SzerConnect in order to contact the contributor Submitted on : Sunday, October 16, 2005 - 8:00:42 PM Last modification on : Friday, February 26, 2021 - 3:28:04 PM Long-term archiving on: : Thursday, April 1, 2010 - 8:34:45 PM
Daniel Szer, François Charpillet. An Optimal Best-first Search Algorithm for Solving Infinite Horizon DEC-POMDPs. 16th European Conference on Machine Learning - ECML'2005, Oct 2005, Porto/Portugal. ⟨inria-00000205⟩