Quantifying the Self-Interest Level of Markov Social Dilemmas

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Willis, Richard, Du, Yali, Leibo, Joel Z, Luck, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913843492421632
author Willis, Richard
Du, Yali
Leibo, Joel Z
Luck, Michael
author_facet Willis, Richard
Du, Yali
Leibo, Joel Z
Luck, Michael
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16138
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantifying the Self-Interest Level of Markov Social Dilemmas
Willis, Richard
Du, Yali
Leibo, Joel Z
Luck, Michael
Computer Science and Game Theory
Multiagent Systems
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.
title Quantifying the Self-Interest Level of Markov Social Dilemmas
topic Computer Science and Game Theory
Multiagent Systems
url https://arxiv.org/abs/2501.16138