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 2401.09547math.OC
收藏

一种通过前向后向得分动力学计算平均场控制问题的深度学习算法

A deep learning algorithm for computing mean field control problems via forward-backward score dynamics

Mo Zhou, Stanley Osher, Wuchen Li

AI总结:

该研究提出一种深度学习方法,利用得分函数构建平均场控制系统的确定性前向后向特征,通过神经网络拟合特征线求解带个体噪声的平均场控制问题,经多类数值算例验证了方法有效性。

摘要:

我们提出一种深度学习方法,用于求解带个体噪声的平均场控制问题。该问题由Fokker-Planck(FP,福克-普朗克)方程和Hamilton-Jacobi-Bellman(HJB,哈密顿-雅可比-贝尔曼)方程构成。利用熵的微分即得分函数,我们首先为平均场控制系统构建了确定性前向后向特征,这不同于经典的前向后向随机微分方程(FBSDEs)。我们进一步应用神经网络逼近拟合所提出的确定性特征线。包含熵势能控制问题、线性二次调节器、系统性风险在内的数值算例验证了所提方法的有效性。

英文摘要:

We propose a deep learning approach to compute mean field control problems with individual noises. The problem consists of the Fokker-Planck (FP) equation and the Hamilton-Jacobi-Bellman (HJB) equation. Using the differential of the entropy, namely the score function, we first formulate the deterministic forward-backward characteristics for the mean field control system, which is different from the classical forward-backward stochastic differential equations (FBSDEs). We further apply the neural network approximation to fit the proposed deterministic characteristic lines. Numerical examples, including the control problem with entropy potential energy, the linear quadratic regulator, and the systemic risks, demonstrate the effectiveness of the proposed method.

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。

↑