{"type":"ScholarlyArticle","title":"Exploration and Adaptation in Multiagent Systems: A Model-based Approach","authors":[{"name":"David Carmel","slug":"david-carmel","given":"David","family":"Carmel","affiliation":""},{"name":"Shaul Markovitch","slug":"shaul-markovitch","given":"Shaul","family":"Markovitch","affiliation":""}],"abstract":"Agents that operate in a multi-agent system can benefit significantly from adapting to other agents while interacting with them. This work presents a general architecture for a modelbased learning strategy combined with an exploration strategy. This combination enables adaptive agents to learn models of their rivals and to explore their behavior for exploitation in future encounters. We report experimental r es ults in the It erated Prisoner's Dilemma domain, demonstrating the superiority of the mod el-based learning agent over non-adaptive agents and over reinforcement-learning agents. The Experimental results also show that exploration can improve the performance of a modelbased agent significantly.","doi":null,"url":"https://ijcai.org/proceedings/1997/89","pdf":"https://ijcai.org/proceedings/1997/0089.pdf","markdown":"https://ijcai.org/proceedings/1997/89.md","bibtex":"https://ijcai.org/proceedings/1997/bibtex/89","volume":{"slug":"1997","title":"Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1997","url":"https://ijcai.org/proceedings/1997/","year":1997,"location":"Nagoya, Japan","dates":"","editors":"Martha E. Pollack","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Distributed Artificial Intelligence","track":"Distributed Artificial Intelligence","number":89,"pages":{"first":606,"last":610},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}