Partner Selection for the Emergence of Cooperation in Multi-Agent Systems Using Reinforcement Learning
This work addresses the challenge of fostering cooperation in selfish multi-agent systems, which is incremental as it builds on existing social dilemma research.
The paper tackled the problem of promoting cooperation in multi-agent systems by investigating partner selection as a mechanism, and found that agents trained with this dynamic learned strategies that retaliated against defectors and fostered cooperation, leading to a prosocial society.
Social dilemmas have been widely studied to explain how humans are able to cooperate in society. Considerable effort has been invested in designing artificial agents for social dilemmas that incorporate explicit agent motivations that are chosen to favor coordinated or cooperative responses. The prevalence of this general approach points towards the importance of achieving an understanding of both an agent's internal design and external environment dynamics that facilitate cooperative behavior. In this paper, we investigate how partner selection can promote cooperative behavior between agents who are trained to maximize a purely selfish objective function. Our experiments reveal that agents trained with this dynamic learn a strategy that retaliates against defectors while promoting cooperation with other agents resulting in a prosocial society.