arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.01096cs.LGcs.CVcs.MA
收藏

大规模多智能体强化学习的代表价值函数方法

Represented Value Function Approach for Large Scale Multi Agent Reinforcement Learning

Artificial Intelligence Research Center of National Innovation Institute of Defense Technology(国防科技大学全国创新研究院人工智能研究中心);Tianjin Artificial Intelligence Innovation Center(天津人工智能创新中心)

Weiya Ren

摘要:

本文研究了大规模多智能体强化学习问题。首先,我们研究了两两价值函数的表示问题,以降低智能体之间交互的复杂性。其次,我们采用了一个l2-范数技巧来保证近似价值函数的平凡项是有界的。最后,通过对战斗游戏的实验结果验证了该方法的有效性。

英文摘要:

In this paper, we consider the problem of large scale multi agent reinforcement learning. Firstly, we studied the representation problem of the pairwise value function to reduce the complexity of the interactions among agents. Secondly, we adopt a l2-norm trick to ensure the trivial term of the approximated value function is bounded. Thirdly, experimental results on battle game demonstrate the effectiveness of the proposed approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑