Adaptive Punishment for Cooperation in Mixed-Motive Games

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Min, Kong, Fanqi, Lü, Linyuan, Feng, Xue
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911713223245824
author Tang, Min
Kong, Fanqi
Lü, Linyuan
Feng, Xue
author_facet Tang, Min
Kong, Fanqi
Lü, Linyuan
Feng, Xue
contents Mixed-motive scenarios are ubiquitous in real-world multi-agent interactions, where self-interested agents often defect for immediate rewards, overlooking the potential of altruistic cooperation to improve long-term gains and collective welfare. Peer punishment can deter defection, but as costly second-order altruism, its persistent imposition may undermine the punisher's interests. Existing approaches often struggle to effectively implement punishment to promote cooperation. To balance the efficacy and cost of punishment, we propose Adaptive Punishment for Cooperation (APC), a distributed method that determines punishment intensity based on both a dynamic punishment probability and the severity of defection. This dynamic probability substantially reduces costly and ineffective punishment while also promotes cooperation. To accurately assess defection and its severity, we use a defection awareness module, whose learning is guided by game reward. Theoretical analysis and empirical results show APC performs effectively in iterated public goods game. Empirically, APC also significantly outperforms existing baselines across sequential social dilemmas, learning rational and effective punishment policies that foster cooperation by strategically deterring defection.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24516
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adaptive Punishment for Cooperation in Mixed-Motive Games
Tang, Min
Kong, Fanqi
Lü, Linyuan
Feng, Xue
Multiagent Systems
Artificial Intelligence
Mixed-motive scenarios are ubiquitous in real-world multi-agent interactions, where self-interested agents often defect for immediate rewards, overlooking the potential of altruistic cooperation to improve long-term gains and collective welfare. Peer punishment can deter defection, but as costly second-order altruism, its persistent imposition may undermine the punisher's interests. Existing approaches often struggle to effectively implement punishment to promote cooperation. To balance the efficacy and cost of punishment, we propose Adaptive Punishment for Cooperation (APC), a distributed method that determines punishment intensity based on both a dynamic punishment probability and the severity of defection. This dynamic probability substantially reduces costly and ineffective punishment while also promotes cooperation. To accurately assess defection and its severity, we use a defection awareness module, whose learning is guided by game reward. Theoretical analysis and empirical results show APC performs effectively in iterated public goods game. Empirically, APC also significantly outperforms existing baselines across sequential social dilemmas, learning rational and effective punishment policies that foster cooperation by strategically deterring defection.
title Adaptive Punishment for Cooperation in Mixed-Motive Games
topic Multiagent Systems
Artificial Intelligence
url https://arxiv.org/abs/2605.24516