{"type":"ScholarlyArticle","title":"Quantifying the Self-Interest Level of Markov Social Dilemmas","authors":[{"name":"Richard Willis","slug":"richard-willis","given":"Richard","family":"Willis","affiliation":""},{"name":"Yali Du","slug":"yali-du","given":"Yali","family":"Du","affiliation":""},{"name":"Joel Z. Leibo","slug":"joel-z-leibo","given":"Joel Z.","family":"Leibo","affiliation":""},{"name":"Michael Luck","slug":"michael-luck","given":"Michael","family":"Luck","affiliation":""}],"abstract":"This paper introduces a novel method for estimating the self-interest level of Markov social dilemmas.\r\nWe extend the concept of self-interest level from normal-form games to Markov games, providing a quantitative measure of the minimum reward exchange required to align individual and collective interests.\r\nWe demonstrate our method on three environments from the Melting Pot suite, representing either common-pool resources or public goods.\r\nOur results illustrate how reward exchange can enable agents to transition from selfish to collective equilibria in a Markov social dilemma.\r\nThis work contributes to multi-agent reinforcement learning by providing a practical tool for analysing complex, multistep social dilemmas.\r\nOur findings offer insights into how reward structures can promote or hinder cooperation, with potential applications in areas such as mechanism design.","doi":"10.24963/ijcai.2025/33","url":"https://ijcai.org/proceedings/2025/33","pdf":"https://ijcai.org/proceedings/2025/0033.pdf","markdown":"https://ijcai.org/proceedings/2025/33.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/33","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Agent-based and Multi-agent Systems","track":"Main Track","number":33,"pages":{"first":284,"last":292},"keywords":["Agent-based and Multi-agent Systems: MAS: Coordination and cooperation","Game Theory and Economic Paradigms: GTEP: Mechanism design","Game Theory and Economic Paradigms: GTEP: Cooperative games","Agent-based and Multi-agent Systems: MAS: Multi-agent learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}