Solving stochastic optimal control problem via stochastic maximum principle with deep learning method

DOI10.1007/s10915-022-01979-5zbMath1497.49042arXiv2007.02227OpenAlexW4297087551WikidataQ114225518 ScholiaQ114225518MaRDI QIDQ2676795

Ying Peng, Shige Peng, Xichuan Zhang, Shaolin Ji

Publication date: 28 September 2022

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.02227

zbMATH Keywords

stochastic controlstochastic maximum principleHamiltonian systemPDEsdeep neural networks

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Discrete approximations in optimal control (49M25) Optimality conditions for problems involving randomness (49K45)

Uses Software

• L-BFGS

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• The rate of convergence of finite-difference approximations for Bellman equations with Lipschitz coefficients
• On the limited memory BFGS method for large scale optimization
• Stochastic maximum principle for distributed parameter systems
• Forward-backward stochastic differential equations and their applications
• Problem of eigenvalues of stochastic Hamiltonian systems with boundary conditions.
• Neural networks-based backward scheme for fully nonlinear PDEs
• Convergence of the deep BSDE method for coupled FBSDEs
• Backward stochastic differential equations and applications to optimal control
• The rate of convergence of finite-difference approximations for parabolic bellman equations with Lipschitz coefficients in cylindrical domains
• ON THE RATE OF CONVERGENCE OF APPROXIMATION SCHEMES FOR BELLMAN EQUATIONS ASSOCIATED WITH OPTIMAL STOPPING TIME PROBLEMS
• A General Stochastic Maximum Principle for Optimal Control Problems
• Dynamic programming and stochastic control processes
• An Introductory Approach to Duality in Optimal Stochastic Control
• Fully Coupled Forward-Backward Stochastic Differential Equations and Applications to Optimal Control
• A Global Stochastic Maximum Principle for Fully Coupled Forward-Backward Stochastic Systems
• Deep backward schemes for high-dimensional nonlinear PDEs
• Solving high-dimensional partial differential equations using deep learning
• Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games I: The Ergodic Case
• Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis
• Nonlinear Expectations and Stochastic Calculus under Uncertainty
• Numerical Methods for Stochastic Control Problems in Continuous Time

This page was built for publication: Solving stochastic optimal control problem via stochastic maximum principle with deep learning method