Integrated Altruistic and Fairness Preference Induces Advanced Mutual Cooperation in Sequential Social Dilemmas
2026-07-06 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors address the challenge of getting multiple agents to cooperate when their individual goals conflict with the group's best outcome, a common issue in multi-agent reinforcement learning. They create a new way to reward agents by combining concern for others' rewards (altruism) and a desire for fairness, calling this the Altruistic and Fairness Preference (AFP). Their experiments show that agents using AFP cooperate better and share rewards more equally than other methods. They also find that altruism helps agents contribute to shared goals, while fairness encourages reciprocity between agents.
multi-agent reinforcement learningsocial dilemmacooperationaltruistic preferencesfairness preferencesreward functionpublic goodsequityinequity aversion
Authors
Yu Wei, Yukiko Ogura, Yoshiyuki Ohmura, Ildefons Magrans de Abril, Hoshinori Kanazawa, Yasuo Kuniyoshi
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.