Learning to Achieve Social Rationality Using Tag Mechanism in Repeated Interactions

Abstract

In multi-agent system, social rationality is a desirable goal to achieve in terms of maximizing the global efficiency of the system. Using tag to select partners in agent populations has been shown to be successful to promote social rationality among agents in prisoner's dilemma game and anticoordination game, but the results are not quite satisfactory. We develop a tag-based learning framework for a population of agents, in which each agent employs a reinforcement learning based strategy instead of using evolutionary learning as in previous works to make their decisions. We evaluate this learning framework in different games and simulation results show that better performance in terms of coordinating on socially rational outcomes can be achieved compared with that in previous work.

Cooperative Multi-Agent Learning in Social Networks: A Review

“…By implementing this technique, the agents were able to achieve much more stable coordination on socially optimal outcomes as compared to the previous approaches. The performance evaluation of this social learning framework was extensively done under the testbed of two-player general-sum games and was compared with previous work [10] [14]. The influences of different factors on the learning performance of the social learning framework were investigated as well.…”