{"type":"ScholarlyArticle","title":"Solving Factored MDPs via Non-Homogeneous Partitioning","authors":[{"name":"Kee-Eung Kim","slug":"kee-eung-kim","given":"Kee-Eung","family":"Kim","affiliation":""},{"name":"Thomas L. Dean","slug":"thomas-l-dean","given":"Thomas L.","family":"Dean","affiliation":""}],"abstract":"This paper describes an algorithm for solving large state-space MDPs (represented as factored MDPs) using search by successive refinement in the space of non-homogeneous partitions. Homogeneity is defined in terms of bisimulation and reward equivalence within blocks of a partition. Since homogeneous partitions that define equivalent reduced state-space MDPs can have a large number of blocks, we relax the requirement of homogeneity. The algorithm constructs approximate aggregate MDPs from non-homogeneous partitions, solves the aggregate MDPs exactly, and then uses the resulting value functions as part of a heuristic in refining the current best non-homogeneous partition. We outline the theory motivating the use of this heuristic and present empirical results and comparisons.","doi":null,"url":"https://ijcai.org/proceedings/2001/94","pdf":"https://ijcai.org/proceedings/2001/0094.pdf","markdown":"https://ijcai.org/proceedings/2001/94.md","bibtex":"https://ijcai.org/proceedings/2001/bibtex/94","volume":{"slug":"2001","title":"Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2001","url":"https://ijcai.org/proceedings/2001/","year":2001,"location":"Seattle, Washington, USA","dates":"","editors":"","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":94,"pages":{"first":683,"last":688},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}