Reinforcement social learning of coordination in cooperative multiagent systems

Coordination in cooperative multiagent systems is an important problem and has received a lot of attention in multiagent learning literature. Most of previous works study the problem of how two (or more) players can coordinate on Pareto-optimal Nash equilibrium(s) through fixed and repeated interactions in the context of cooperative games. However, in practical complex environments, the interactions between agents can be sparse, and each agent's interacting partners may change frequently and randomly. To this end, in this paper, we investigate the multiagent coordination problems in cooperative environments under the social learning framework, in which there exists a large population of agents and each agent interacts with another agent randomly in each round. Each agent learns its policy through repeated interactions with the rest of agents via social learning. We distinguish two different types of learners depending on the amount of information each agent can perceive: individual action learner and joint action learner. The learning performance of both types of learners are evaluated under a number of challenging deterministic and stochastic cooperative games.