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 2511.04515math.OCmath.PRq-fin.MF
收藏

共同噪声不确定性下的鲁棒平均场控制

Robust mean-field control under common noise uncertainty

Shanghai Frontiers Science Center of Artificial Intelligence(上海人工智能前沿科学中心);NYU-ECNU Institute of Mathematical Sciences, NYU Shanghai(纽约大学华东师范大学数学科学研究所,纽约大学上海分校);Division of Mathematical Sciences, Nanyang Technological University(南洋理工大学数学科学学院)

Mathieu Laurière, Ariel Neufeld, Kyunghyun Park

AI总结:

本文提出离散时间共同噪声不确定性下的鲁棒平均场控制框架,证明其作为N智能体合作鲁棒优化问题混沌传播极限,并通过提升鲁棒马尔可夫决策问题建立动态规划原理与Bellman--Isaac不动点定理证明最优开环控制存在,数值实验验证了考虑共同噪声不确定性的优势。

摘要:

我们提出并分析了一个离散时间鲁棒平均场控制问题的框架,该框架考虑共同噪声不确定性。在此框架中,平均场交互描述了无穷多个合作智能体的状态和行动的集体行为,而共同噪声——一种影响所有智能体状态动态的随机扰动——是不确定的。一个社会规划者在无限时域上对开环控制进行优化,以最大化代表性智能体的最坏情况期望奖励,其中最坏情况对应于所有候选概率测度中最不利的那个测度,这些候选测度诱导了共同噪声过程未知的真实律。我们将这一优化问题称为共同噪声不确定性下的鲁棒平均场控制问题。我们首先证明该问题是合作N智能体鲁棒优化问题的渐近极限,即通常所称的混沌传播。然后,通过将鲁棒平均场控制问题与概率测度空间上的提升鲁棒马尔可夫决策问题联系起来,并建立提升鲁棒马尔可夫决策问题的动态规划原理和Bellman--Isaac不动点定理,我们证明了最优开环控制的存在性。最后,我们以分布规划和金融中的系统性风险为动机进行数值实验,补充了理论结果,突显了考虑共同噪声不确定性的优势。

英文摘要:

We propose and analyze a framework for discrete-time robust mean-field control problems under common noise uncertainty. In this framework, the mean-field interaction describes the collective behavior of infinitely many cooperative agents' state and action, while the common noise -- a random disturbance affecting all agents' state dynamics -- is uncertain. A social planner optimizes over open-loop controls on an infinite horizon to maximize the representative agent's worst-case expected reward, where worst-case corresponds to the most adverse probability measure among all candidates inducing the unknown true law of the common noise process. We refer to this optimization as a robust mean-field control problem under common noise uncertainty. We first show that this problem arises as the asymptotic limit of a cooperative $N$-agent robust optimization problem, commonly known as propagation of chaos. We then prove the existence of an optimal open-loop control by linking the robust mean field control problem to a lifted robust Markov decision problem on the space of probability measures and by establishing the dynamic programming principle and Bellman--Isaac fixed point theorem for the lifted robust Markov decision problem. Finally, we complement our theoretical results with numerical experiments motivated by distribution planning and systemic risk in finance, highlighting the advantages of accounting for common noise uncertainty.

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。

↑