Proceedings

Quantifying the Self-Interest Level of Markov Social Dilemmas

Richard Willis, Yali Du, Joel Z. Leibo, Michael Luck

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 284-292.

https://doi.org/10.24963/ijcai.2025/33

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

Abstract

This paper introduces a novel method for estimating the self-interest level of Markov social dilemmas.

We 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.

We demonstrate our method on three environments from the Melting Pot suite, representing either common-pool resources or public goods.

Our results illustrate how reward exchange can enable agents to transition from selfish to collective equilibria in a Markov social dilemma.

This work contributes to multi-agent reinforcement learning by providing a practical tool for analysing complex, multistep social dilemmas.

Our findings offer insights into how reward structures can promote or hinder cooperation, with potential applications in areas such as mechanism design.

Richard Willis, Yali Du, Joel Z. Leibo, and Michael Luck. 2025. Quantifying the Self-Interest Level of Markov Social Dilemmas. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 284–292. https://doi.org/10.24963/ijcai.2025/33
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards