arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.00587cs.LGcs.AIcs.MAstat.ML
收藏

基于价值因子分解的多Agent协作Q学习研究

Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization

Tsinghua University(清华大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Jianhao Wang, Zhizhou Ren, Beining Han, Jianing Ye, Chongjie Zhang

摘要:

价值因子分解是一种在协作环境中扩展多智能体强化学习的流行和有前途的方法,它平衡了学习的可扩展性和价值函数的表示能力。然而,这种方法的理论理解是有限的。在本文中,我们形式化的多智能体拟合Q-迭代框架分析因子化多智能体Q-学习。基于这个框架,我们调查线性值分解,并揭示了多智能体Q学习与这个简单的分解隐含地实现了一个强大的反事实信用分配,但可能不会收敛在某些设置。通过进一步的分析,我们发现,在政策上的训练或更丰富的联合价值函数类可以改善其局部或全局收敛性能。最后,为了支持我们在实际实现中的理论含义,我们对最先进的深度多智能体Q-学习算法在教学示例和广泛的星际争霸II单元微观管理任务上进行了实证分析。

英文摘要:

Value factorization is a popular and promising approach to scaling up multi-agent reinforcement learning in cooperative settings, which balances the learning scalability and the representational capacity of value functions. However, the theoretical understanding of such methods is limited. In this paper, we formalize a multi-agent fitted Q-iteration framework for analyzing factorized multi-agent Q-learning. Based on this framework, we investigate linear value factorization and reveal that multi-agent Q-learning with this simple decomposition implicitly realizes a powerful counterfactual credit assignment, but may not converge in some settings. Through further analysis, we find that on-policy training or richer joint value function classes can improve its local or global convergence properties, respectively. Finally, to support our theoretical implications in practical realization, we conduct an empirical analysis of state-of-the-art deep multi-agent Q-learning algorithms on didactic examples and a broad set of StarCraft II unit micromanagement tasks.

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。

↑