Multi-agent Learning For Game-theoretical Problems

Multi-agent systems are prevalent in the real world in various domains. In many multi-agent systems, interaction among agents is inevitable, and cooperation in some form is needed among agents to deal with the task at hand. We model the type of multi-agent systems where autonomous agents inhabit an environment with no global control or global knowledge, decentralized in the true sense. In particular, we consider game-theoretical problems such as the hedonic coalition formation games, matching problems, and Cournot games. We propose novel decentralized learning and multi-agent reinforcement learning approaches to train agents in learning behaviors and adapting to the environments. We use game-theoretic evaluation criteria such as optimality, stability, and resulting equilibria