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.
@article{arxiv.2501.16138,
title = {Quantifying the Self-Interest Level of Markov Social Dilemmas},
author = {Richard Willis and Yali Du and Joel Z Leibo and Michael Luck},
journal= {arXiv preprint arXiv:2501.16138},
year = {2025}
}