arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2109.09034cs.LGcs.MAstat.ML
收藏

贪婪的UnMixing用于多智能体强化学习中的Q学习

Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning

University of Technology Sydney(悉尼科技大学);Faculty of Engineering and Information Technology(工程与信息技术学院)

Chapman Siu, Jason Traish, Richard Yi Da Xu

摘要:

本文介绍了贪婪Unmix(GUM)的合作多智能体强化学习(MARL)。Greedy UnMix旨在避免MARL方法由于高估作为大型联合状态-动作空间的一部分的值而失败的情况。它旨在通过一种保守的Q学习方法来解决这个问题,通过限制数据集中的状态边缘来避免未观察到的联合状态动作空间,同时尝试在分散执行范式的集中式训练下分解或简化问题空间。我们证明了在MARL场景的Q-学习中坚持Q-函数下限,并在一组基准MARL任务上表现出优于现有Q-学习MARL方法以及更一般的MARL算法的性能,尽管与最先进的方法相比相对简单。

英文摘要:

This paper introduces Greedy UnMix (GUM) for cooperative multi-agent reinforcement learning (MARL). Greedy UnMix aims to avoid scenarios where MARL methods fail due to overestimation of values as part of the large joint state-action space. It aims to address this through a conservative Q-learning approach through restricting the state-marginal in the dataset to avoid unobserved joint state action spaces, whilst concurrently attempting to unmix or simplify the problem space under the centralized training with decentralized execution paradigm. We demonstrate the adherence to Q-function lower bounds in the Q-learning for MARL scenarios, and demonstrate superior performance to existing Q-learning MARL approaches as well as more general MARL algorithms over a set of benchmark MARL tasks, despite its relative simplicity compared with state-of-the-art approaches.

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。

↑