arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.05744math.NAcs.LGcs.NAstat.ML
收藏

高维抛物型Hamilton-Jacobi-Bellman方程的深度神经网络逼近

Deep neural network approximation for high-dimensional parabolic Hamilton-Jacobi-Bellman equations

Faculty of Mathematics, University of Vienna(维也纳大学数学学院);Johann Radon Institute for Computational and Applied Mathematics, Austrian Academy of Sciences(奥地利科学院约翰·拉东计算与应用数学研究所)

Philipp Grohs, Lukas Herrmann

摘要:

研究了深度神经网络对二阶Hamilton-Jacobi-Bellman(HJB)方程解的逼近.结果表明,对于HJB方程的某些马尔可夫过程的最优控制的上下文中出现的解决方案可以近似的深度神经网络,而不会招致灾难的尺寸。动力学被假定为依赖于控制和二次依赖于控制的成本。容许控制在有界集中取值。

英文摘要:

The approximation of solutions to second order Hamilton--Jacobi--Bellman (HJB) equations by deep neural networks is investigated. It is shown that for HJB equations that arise in the context of the optimal control of certain Markov processes the solution can be approximated by deep neural networks without incurring the curse of dimension. The dynamics is assumed to depend affinely on the controls and the cost depends quadratically on the controls. The admissible controls take values in a bounded set.

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。

↑