Integrated Altruistic and Fairness Preference Induces Advanced Mutual Cooperation in Sequential Social Dilemmas

2026-07-06

AI Summary

This work addresses the challenge in multi-agent reinforcement learning where individual rationality often leads to collectively suboptimal outcomes in social dilemmas. To overcome this, the paper proposes a novel utility function—Altruism and Fairness Preference (AFP)—that unifies two well-established social psychological preferences into a reward-sharing mechanism. For the first time, altruistic and fairness-oriented motivations are integrated to jointly transform self and others’ rewards into cooperative incentives, thereby fostering reciprocal cooperation in sequential social dilemmas. Experimental results demonstrate that agents equipped with AFP significantly outperform existing baselines across two challenging social dilemma tasks, achieving higher collective returns and improved outcome fairness. The study further reveals the distinct yet complementary roles of altruism and fairness in promoting cooperative behavior.

Abstract

Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in social dilemma situations. There, individual interests are misaligned with the common good and individual rationality leads to suboptimal group outcomes. In contrast, humans are able to achieve cooperation with one another in such situations. A common explanation for such cooperative behavior is that individuals have social preferences. In order to achieve cooperation in MARL, we design a new utility function integrating altruistic preferences (incentive for other's reward) and fairness preferences (incentive for equality) from social psychology and behavioral economics, namely, Altruistic and Fairness Preference (AFP), a reward-sharing mechanism which converts one's own and other's rewards to incentives for cooperative behavior. We performed comparative experiments with standard RL and inequity aversion agents in two challenging sequential social dilemma games, and showed that AFP agents successfully achieved mutual cooperation with more collective rewards and higher equity than the baselines. To further understand the progression of AFP during training, we subsequently explore the effects of altruistic preferences and fairness preferences on agents' behavior. The results suggest that altruistic preferences encourage agents to contribute to the public goods, and fairness preferences induce mutual behavior between agents.

Problem

• multi-agent reinforcement learning
• social dilemmas
• cooperation
• altruistic preference
• fairness preference

Innovation

• Altruistic Preference
• Fairness Preference
• Multi-Agent Reinforcement Learning
• Social Dilemma
• Reward Sharing