{"type":"ScholarlyArticle","title":"Average-Reward Decentralized Markov Decision Processes","authors":[{"name":"Marek Petrik","slug":"marek-petrik","given":"Marek","family":"Petrik","affiliation":""},{"name":"Shlomo Zilberstein","slug":"shlomo-zilberstein","given":"Shlomo","family":"Zilberstein","affiliation":""}],"abstract":"Formal analysis of decentralized decision making has become a thriving research area in recent years, producing a number of multi-agent extensions of Markov decision processes. While much of the work has focused on optimizing discounted cumulative reward, optimizing average reward is sometimes a more suitable criterion. We formalize a class of such problems and analyze its characteristics, showing that it is NP complete and that optimal policies are deterministic. Our analysis lays the foundation for designing two optimal algorithms. Experimental results with a standard problem from the literature illustrate the applicability of these solution techniques.","doi":null,"url":"https://ijcai.org/proceedings/2007/322","pdf":"https://ijcai.org/proceedings/2007/0322.pdf","markdown":"https://ijcai.org/proceedings/2007/322.md","bibtex":"https://ijcai.org/proceedings/2007/bibtex/322","volume":{"slug":"2007","title":"Proceedings of the Twentieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2007","url":"https://ijcai.org/proceedings/2007/","year":2007,"location":"Hyderabad, India","dates":"","editors":"Ramon López de Mántaras","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":322,"pages":{"first":1997,"last":2001},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}