arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.06192math.OC
收藏

不对跟随者建模的强凸光滑Stackelberg对策

Solving Strongly Convex and Smooth Stackelberg Games Without Modeling the Follower

Yansong Li, Shuo Han

摘要:

Stackelberg博弈已被广泛用于建模各种领域的交互决策问题,如能源系统,交通,网络安全和人机交互。然而,现有的解决Stackelberg游戏的算法往往需要的追随者的费用函数或学习动态的知识,也可能需要追随者提供一个确切的最佳响应,这可能是难以获得在实践中。为了规避这个困难,我们开发了一种算法,不需要跟随者的费用函数或确切的最佳响应的知识,使其更适用于现实世界的情况。具体来说,我们的算法只需要追随者提供一个近似最优的行动,以响应领导者的行动。该方法利用不精确最佳响应函数计算领导者目标函数的近似梯度,并利用该梯度进行零阶二层优化,得到领导者的最优行动。当领导者的费用函数在跟随者的最佳反应下是强凸的且光滑的时,我们的算法被证明以线性速度收敛到最优点的一个邻域。

英文摘要:

Stackelberg games have been widely used to model interactive decision-making problems in a variety of domains such as energy systems, transportation, cybersecurity, and human-robot interaction. However, existing algorithms for solving Stackelberg games often require knowledge of the follower's cost function or learning dynamics and may also require the follower to provide an exact best response, which can be difficult to obtain in practice. To circumvent this difficulty, we develop an algorithm that does not require knowledge of the follower's cost function or an exact best response, making it more applicable to real-world scenarios. Specifically, our algorithm only requires the follower to provide an approximately optimal action in response to the leader's action. The inexact best response is used in computing an approximate gradient of the leader's objective function, with which zeroth-order bilevel optimization can be applied to obtain an optimal action for the leader. Our algorithm is proved to converge at a linear rate to a neighborhood of the optimal point when the leader's cost function under the follower's best response is strongly convex and smooth.

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。

↑