mlsanityData to 13 Oct 2026

Adaptive Punishment for Cooperation in Mixed-Motive Games

arXiv 2605.24516 ↗First posted 23 May 2026cs.MA cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 15 of its 26 references that are in the map. First posted on arXiv 23 May 2026.

Builds on

15 of 26 references.

References · 15

  1. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,223
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,525
  3. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 493
  4. 2017Learning with Opponent-Learning Awarenesscited by 220
  5. 2018Inequity aversion improves cooperation in intertemporal social dilemmascited by 106
  6. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 97
  7. 2017A multi-agent reinforcement learning model of common-pool resource appropriationcited by 68
  8. 2017Maintaining cooperation in complex social dilemmas using deep reinforcement learningcited by 48
  9. 2017Prosocial learning agents solve generalized Stag Hunts better than selfish onescited by 47
  10. 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Makingcited by 19
  11. 2020D3C: Reducing the Price of Anarchy in Multi-Agent Learningcited by 16
  12. 2024Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planningcited by 7
3 more
  1. 2024Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Gamescited by 6
  2. 2022The emergence of division of labor through decentralized social sanctioningcited by 5
  3. 2023Investigating the Impact of Direct Punishment on the Emergence of Cooperation in Multi-Agent Reinforcement Learning Systemscited by 5

Built on by

Not cited yet.