A game-theoretic learning model in multi-agent systems

This paper investigates the problem of learning in multi-agent system that can be applied to tele- communication networks. We model the strategic inter- dependence situation and learning dynamics of self- interested agents in the framework of Markov game with. incomplete information. By combining fictitious play's best response strategy and Nash Q-learning's multi-agent Q-learning, we propose a new multi-agent learning algorithm that can maximize learning agent's expected reward and optimize system-wide performance. We also summarize other algorithms from the game theory and reinforcement learning communities, and compare these algorithms with ours.