arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.06253cs.GTcs.SYeess.SYmath.DS
收藏

具有动态群体的时变单调网络博弈中的学习

Learning in Time-Varying Monotone Network Games with Dynamic Populations

Feras Al Taha, Kiran Rokade, Francesca Parise

AI总结:

本文研究动态网络环境下多智能体投影梯度学习,证明所学策略几乎必然收敛到期望成本博弈的纳什均衡,并给出高概率近似纳什均衡性质及非渐近遗憾界。

摘要:

在本文中,我们提出了一个用于非平稳动态网络环境中多智能体学习的框架。更具体地说,我们研究了平滑单调重复网络博弈中的投影梯度策略,其中智能体的参与和连接随时间变化。我们用一个随机网络来建模这个变化的系统,该网络在每次重复时都会产生一个新的独立实现。我们证明,智能体通过网络实现序列上的投影梯度动力学所学到的策略配置,几乎必然且在均方意义下收敛到博弈的纳什均衡,在该均衡中玩家最小化其期望成本。然后我们证明,所学到的策略配置以高概率是智能体在重复博弈每个阶段所进行博弈的近似纳什均衡。利用这两个结果,我们推导出智能体所产生遗憾的非渐近界。

英文摘要:

In this paper, we present a framework for multi-agent learning in a nonstationary dynamic network environment. More specifically, we examine projected gradient play in smooth monotone repeated network games in which the agents' participation and connectivity vary over time. We model this changing system with a stochastic network which takes a new independent realization at each repetition. We show that the strategy profile learned by the agents through projected gradient dynamics over the sequence of network realizations converges to a Nash equilibrium of the game in which players minimize their expected cost, almost surely and in the mean-square sense. We then show that the learned strategy profile is an almost Nash equilibrium of the game played by the agents at each stage of the repeated game with high probability. Using these two results, we derive non-asymptotic bounds on the regret incurred by the agents.

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。

↑