{"type":"ScholarlyArticle","title":"Predicting and Preventing Coordination Problems in Cooperative Q-learning Systems","authors":[{"name":"Nancy Fulda","slug":"nancy-fulda","given":"Nancy","family":"Fulda","affiliation":""},{"name":"Dan Ventura","slug":"dan-ventura","given":"Dan","family":"Ventura","affiliation":""}],"abstract":"We present a conceptual framework for creating Q-learning-based algorithms that converge to optimal equilibria in cooperative multiagent settings. This framework includes a set of conditions that are sufficient to guarantee optimal system performance. We demonstrate the efficacy of the framework by using it to analyze several well-known multi-agent learning algorithms and conclude by employing it as a design tool to construct a simple, novel multiagent learning algorithm.","doi":null,"url":"https://ijcai.org/proceedings/2007/125","pdf":"https://ijcai.org/proceedings/2007/0125.pdf","markdown":"https://ijcai.org/proceedings/2007/125.md","bibtex":"https://ijcai.org/proceedings/2007/bibtex/125","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":125,"pages":{"first":780,"last":784},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}