Multi-agent cooperation by reinforcement learning with teammate modeling and reward allotment
Multi-agent cooperation by reinforcement learning with teammate modeling and reward allotment
复制标题
通过强化学习与队友建模和奖励分配进行多智能体合作
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Huiyan Shen
中科院分区：
文献类型：
--
作者：
Pucheng Zhou;Huiyan Shen
如何通过学习协调不同Agent的行为是多Agent领域中的一个具有挑战性的问题。提出了一种学习多个合作智能体协调动作的强化学习算法。该算法结合了多智能体Q学习框架中的队友建模和奖励分配机制的优点。通过狩猎游戏验证了该算法的有效性。
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.