{"type":"ScholarlyArticle","title":"Point-based value iteration: An anytime algorithm for POMDPs","authors":[{"name":"Joelle Pineau","slug":"joelle-pineau","given":"Joelle","family":"Pineau","affiliation":""},{"name":"Geoffrey J. Gordon","slug":"geoffrey-j-gordon","given":"Geoffrey J.","family":"Gordon","affiliation":""},{"name":"Sebastian Thrun","slug":"sebastian-thrun","given":"Sebastian","family":"Thrun","affiliation":""}],"abstract":"This paper introduces the Point-Based Value Iteration ~PBVI) algorithm for POMDP planning. PBVI approxImates an exact value iteration solution by selecting a small set of representative belief points and then tracking the value and its derivative for those points only. By using_s to~h.astic trajectories to choose belief points, and by mamtammg only one value hyper-plane per point, PBVI successfully solves large problems: we present results on a robotic laser tag problem as well as three test domains from the literature.","doi":null,"url":"https://ijcai.org/proceedings/2003/146","pdf":"https://ijcai.org/proceedings/2003/0146.pdf","markdown":"https://ijcai.org/proceedings/2003/146.md","bibtex":"https://ijcai.org/proceedings/2003/bibtex/146","volume":{"slug":"2003","title":"Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2003","url":"https://ijcai.org/proceedings/2003/","year":2003,"location":"Acapulco, Mexico","dates":"","editors":"Georg Gottlob","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":146,"pages":{"first":1025,"last":1031},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}