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 2212.12561eess.SYcs.LGcs.MAcs.SYmath.OC
收藏

一种求解竞争性多智能体决策与控制问题的主动学习方法

An active learning method for solving competitive multi-agent decision-making and control problems

IMT School for Advanced Studies Lucca(卢cca高等研究院)

Filippo Fabiani, Alberto Bemporad

AI总结:

该研究提出一种主动学习方案,通过集中式观察者探测竞争性多智能体反应并更新动作-反应映射估计,在一般假设下建立参数收敛即得平稳动作剖面的充分条件,数值仿真验证了方法有效性。

摘要:

为识别一群各自执行私有策略的竞争性智能体的平稳动作剖面,我们提出了一种新颖的主动学习方案:集中式外部观察者(或实体)可探测智能体的反应,并递归更新动作-反应映射的简单局部参数化估计。在极为一般的工作假设下(甚至不假设平稳剖面存在),我们建立了充分条件来评估所提主动学习方法的渐近性质,使得当刻画动作-反应映射的参数收敛时,即可得到平稳动作剖面。这些条件也因此可作为该剖面存在性的证明。针对典型竞争性多智能体控制与决策问题开展的大量数值仿真,验证了所提基于学习的方法的实际有效性。

英文摘要:

To identify a stationary action profile for a population of competitive agents, each executing private strategies, we introduce a novel active-learning scheme where a centralized external observer (or entity) can probe the agents' reactions and recursively update simple local parametric estimates of the action-reaction mappings. Under very general working assumptions (not even assuming that a stationary profile exists), sufficient conditions are established to assess the asymptotic properties of the proposed active learning methodology so that, if the parameters characterizing the action-reaction mappings converge, a stationary action profile is achieved. Such conditions hence act also as certificates for the existence of such a profile. Extensive numerical simulations involving typical competitive multi-agent control and decision-making problems illustrate the practical effectiveness of the proposed learning-based approach.

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。

↑