{"type":"ScholarlyArticle","title":"Bounded Policy Iteration for Decentralized POMDPs","authors":[{"name":"Daniel S. Bernstein","slug":"daniel-s-bernstein","given":"Daniel S.","family":"Bernstein","affiliation":""},{"name":"Eric A. Hansen","slug":"eric-a-hansen","given":"Eric A.","family":"Hansen","affiliation":""},{"name":"Shlomo Zilberstein","slug":"shlomo-zilberstein","given":"Shlomo","family":"Zilberstein","affiliation":""}],"abstract":"We present a bounded policy iteration algorithm for infinite-horizon decentralized POMDPs. Policies are represented as joint stochastic finite-state controllers, which consist of a local controller for each agent. We also let a joint controller include a correlation device that allows the agents to correlate their behavior without exchanging information during execution, and show that this leads to improved performance. The algorithm uses a fixed amount of memory, and each iteration is guaranteed to produce a controller with value at least as high as the previous one for all possible initial state distributions. For the case of a single agent, the algorithm reduces to Poupart and Boutilier’s bounded policy iteration for POMDPs.","doi":null,"url":"https://ijcai.org/proceedings/2005/18","pdf":"https://ijcai.org/proceedings/2005/0018.pdf","markdown":"https://ijcai.org/proceedings/2005/18.md","bibtex":"https://ijcai.org/proceedings/2005/bibtex/18","volume":{"slug":"2005","title":"Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2005","url":"https://ijcai.org/proceedings/2005/","year":2005,"location":"Edinburgh, Scotland, UK","dates":"","editors":"","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":18,"pages":{"first":1287,"last":1291},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}