Adaptive Mechanism Design: Learning to Promote Cooperation
This addresses the challenge of ensuring cooperative behavior in multi-agent systems, which is crucial for applications involving AI interactions, though it appears incremental as it builds on existing mechanism design concepts.
The paper tackles the problem of promoting cooperation among artificial learning agents in social dilemmas by having an external agent distribute rewards and punishments based on observed actions, resulting in high social welfare in matrix games where agents would otherwise defect with high probability, with cooperative outcomes sometimes becoming stable without ongoing intervention.
In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We consider the problem of how an external agent can promote cooperation between artificial learners by distributing additional rewards and punishments based on observing the learners' actions. We propose a rule for automatically learning how to create right incentives by considering the players' anticipated parameter updates. Using this learning rule leads to cooperation with high social welfare in matrix games in which the agents would otherwise learn to defect with high probability. We show that the resulting cooperative outcome is stable in certain games even if the planning agent is turned off after a given number of episodes, while other games require ongoing intervention to maintain mutual cooperation. However, even in the latter case, the amount of necessary additional incentives decreases over time.