arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.03055cs.MAcs.LGcs.ROcs.SYeess.SY
收藏

通信范围受限下线性二次网络控制的分布式策略梯度

Distributed Policy Gradient for Linear Quadratic Networked Control with Limited Communication Range

Tsinghua University(清华大学);Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心)

Yuzi Yan, Yuan Shen

AI总结:

针对通信范围受限的多智能体线性二次网络控制问题,提出可扩展分布式策略梯度方法,证明仅用局部信息可逼近精确梯度、性能随通信与控制范围增大指数收敛至最优,还揭示通信范围与稳定性的权衡,仿真验证了理论结果。

摘要:

本文提出一种可扩展的分布式策略梯度方法,并证明其在多智能体线性二次网络系统中可收敛至近似最优解。智能体在特定网络中受局部通信约束,即每个智能体仅能与有限数量的相邻智能体交换信息。在网络的底层图上,每个智能体在线性二次控制场景下,依据邻近邻居的状态执行控制输入。我们证明仅利用局部信息即可逼近精确梯度。与集中式最优控制器相比,随着通信范围和控制范围增大,性能差距呈指数级下降至零。我们还阐明了增大通信范围如何提升梯度下降过程中的系统稳定性,从而揭示了一项关键权衡。仿真结果验证了我们的理论发现。

英文摘要:

This paper proposes a scalable distributed policy gradient method and proves its convergence to near-optimal solution in multi-agent linear quadratic networked systems. The agents engage within a specified network under local communication constraints, implying that each agent can only exchange information with a limited number of neighboring agents. On the underlying graph of the network, each agent implements its control input depending on its nearby neighbors' states in the linear quadratic control setting. We show that it is possible to approximate the exact gradient only using local information. Compared with the centralized optimal controller, the performance gap decreases to zero exponentially as the communication and control ranges increase. We also demonstrate how increasing the communication range enhances system stability in the gradient descent process, thereby elucidating a critical trade-off. The simulation results verify our theoretical findings.

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。

↑