arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.07848cs.AIcs.MA
收藏

面向多样化Q向量的深度网络多智能体强化学习

Multi-agent Reinforcement Learning with Deep Networks for Diverse Q-Vectors

School of Engineering, The University of Newcastle(纽卡斯尔大学工程学院)

Zhenglong Luo, Zhiyong Chen, James Welsh

AI总结:

本文提出一种可利用Max、Nash和Maximin策略学习多样化Q向量的DQN算法,并通过双臂机器人协作抬锅实验验证其有效性。

摘要:

多智能体强化学习(MARL)因其能够促进复杂环境中的学习,已成为一个重要的研究课题。在多智能体任务中,状态-动作价值(通常称为Q值)可能因各智能体的个体奖励不同而在智能体之间存在差异,从而形成Q向量。确定最优策略具有挑战性,因为这不仅仅涉及最大化单个Q值。在此背景下,研究者已经研究了多种最优策略,例如Nash均衡。Nash Q-learning和Nash Actor-Critic等算法已在这些场景中展现出有效性。本文通过提出一种深度Q网络(DQN)算法扩展了该研究,该算法能够使用Max、Nash和Maximin策略学习多种Q向量。该方法的有效性在一个双臂机器人协作抬起锅的环境中得到了验证。

英文摘要:

Multi-agent reinforcement learning (MARL) has become a significant research topic due to its ability to facilitate learning in complex environments. In multi-agent tasks, the state-action value, commonly referred to as the Q-value, can vary among agents because of their individual rewards, resulting in a Q-vector. Determining an optimal policy is challenging, as it involves more than just maximizing a single Q-value. Various optimal policies, such as a Nash equilibrium, have been studied in this context. Algorithms like Nash Q-learning and Nash Actor-Critic have shown effectiveness in these scenarios. This paper extends this research by proposing a deep Q-networks (DQN) algorithm capable of learning various Q-vectors using Max, Nash, and Maximin strategies. The effectiveness of this approach is demonstrated in an environment where dual robotic arms collaborate to lift a pot.

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。

↑