Multi-agent cooperation by reinforcement learning with teammate modeling and reward allotment
Pucheng Zhou, Huiyan Shen · 2011
How to coordinate the behavior of different agents through learning is a challenging problem within multi-agent domains. This paper addressed a kind of reinforcement learning algorithm to learn coordinated actions of a group of cooperative agents. This algorithm combines advantages of teammate modeling and reward allotment mechanism in a multi-agent Q-learning framework. The effectiveness of the proposed algorithm is demonstrated using the hunting game.