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 2305.07856cs.MAcs.AI
收藏

Stackelberg决策变换器用于多智能体系统中的异步动作协调

Stackelberg Decision Transformer for Asynchronous Action Coordination in Multi-Agent Systems

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);SenseTime Research(商汤科技研究院)

Bin Zhang, Hangyu Mao, Lijuan Li, Zhiwei Xu, Dapeng Li, Rui Zhao, Guoliang Fan

AI总结:

针对多智能体系统中异步动作协调的可扩展性难题,提出Stackelberg决策变换器(STEER),融合层级决策、序列建模与探索学习,收敛至均衡解并优于现有方法。

摘要:

异步动作协调是多智能体系统(MAS)中普遍存在的挑战,可建模为Stackelberg博弈(SG)。然而,现有基于SG的多智能体强化学习(MARL)方法的可扩展性严重受限于网络结构或环境限制。为解决此问题,我们提出Stackelberg决策变换器(STEER),一种启发式方法,用于解决智能体间的层级协调难题。STEER通过融合SG的层级决策结构、自回归序列模型的建模能力以及MARL的探索性学习方法,高效管理空间和时间上下文中的决策过程。我们的研究促进了有效且适应性强的异步动作协调方法的发展,该方法可广泛应用于MAS中各种任务类型和环境配置。实验结果表明,我们的方法能够收敛到Stackelberg均衡解,并在复杂场景中优于其他现有方法。

英文摘要:

Asynchronous action coordination presents a pervasive challenge in Multi-Agent Systems (MAS), which can be represented as a Stackelberg game (SG). However, the scalability of existing Multi-Agent Reinforcement Learning (MARL) methods based on SG is severely constrained by network structures or environmental limitations. To address this issue, we propose the Stackelberg Decision Transformer (STEER), a heuristic approach that resolves the difficulties of hierarchical coordination among agents. STEER efficiently manages decision-making processes in both spatial and temporal contexts by incorporating the hierarchical decision structure of SG, the modeling capability of autoregressive sequence models, and the exploratory learning methodology of MARL. Our research contributes to the development of an effective and adaptable asynchronous action coordination method that can be widely applied to various task types and environmental configurations in MAS. Experimental results demonstrate that our method can converge to Stackelberg equilibrium solutions and outperforms other existing methods in complex scenarios.

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。

↑