Solving stochastic optimal control problem via stochastic maximum principle with deep learning method
From MaRDI portal
Publication:2676795
Abstract: In this paper, we aim to solve the high dimensional stochastic optimal control problem from the view of the stochastic maximum principle via deep learning. By introducing the extended Hamiltonian system which is essentially an FBSDE with a maximum condition, we reformulate the original control problem as a new one. Three algorithms are proposed to solve the new control problem. Numerical results for different examples demonstrate the effectiveness of our proposed algorithms, especially in high dimensional cases. And an important application of this method is to calculate the sub-linear expectations, which correspond to a kind of fully nonlinear PDEs.
Recommendations
- Deep learning for constrained utility maximisation
- Stochastic optimal control via forward and backward stochastic differential equations and importance sampling
- Stochastic \(L^1\)-optimal control via forward and backward sampling
- New approach to stochastic optimal control
- Regression methods for stochastic control problems and their convergence analysis
Cites work
- A General Stochastic Maximum Principle for Optimal Control Problems
- A global stochastic maximum principle for fully coupled forward-backward stochastic systems
- An Introductory Approach to Duality in Optimal Stochastic Control
- Backward stochastic differential equations and applications to optimal control
- Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. I: The ergodic case
- Convergence of the deep BSDE method for coupled FBSDEs
- Deep backward schemes for high-dimensional nonlinear PDEs
- Deep learning
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis
- Dynamic programming and stochastic control processes
- Forward-backward stochastic differential equations and their applications
- Fully Coupled Forward-Backward Stochastic Differential Equations and Applications to Optimal Control
- scientific article; zbMATH DE number 1577097 (Why is no real title available?)
- scientific article; zbMATH DE number 1325009 (Why is no real title available?)
- scientific article; zbMATH DE number 3797647 (Why is no real title available?)
- Neural networks-based backward scheme for fully nonlinear PDEs
- Nonlinear expectations and stochastic calculus under uncertainty. With robust CLT and G-Brownian motion
- Numerical Methods for Stochastic Control Problems in Continuous Time
- On the limited memory BFGS method for large scale optimization
- ON THE RATE OF CONVERGENCE OF APPROXIMATION SCHEMES FOR BELLMAN EQUATIONS ASSOCIATED WITH OPTIMAL STOPPING TIME PROBLEMS
- Problem of eigenvalues of stochastic Hamiltonian systems with boundary conditions.
- Solving high-dimensional partial differential equations using deep learning
- Stochastic maximum principle for distributed parameter systems
- The rate of convergence of finite-difference approximations for Bellman equations with Lipschitz coefficients
- The rate of convergence of finite-difference approximations for parabolic bellman equations with Lipschitz coefficients in cylindrical domains
Cited in
(22)- Solving higher-dimensional continuous-time stochastic control problems by value function regression
- Tensor decomposition and high-performance computing for solving high-dimensional stochastic control system numerically
- Deep learning for constrained utility maximisation
- A mean-field optimal control formulation of deep learning
- Solving stochastic optimal control problems by a Wiener chaos approach
- Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications
- An approach to solving optimal control problems of nonlinear systems by introducing detail-reward mechanism in deep reinforcement learning
- Regression methods for stochastic control problems and their convergence analysis
- SympOCnet: Solving Optimal Control Problems with Applications to High-Dimensional Multiagent Path Planning Problems
- Convergence of a Robust Deep FBSDE Method for Stochastic Control
- Value-Gradient Based Formulation of Optimal Control Problem and Machine Learning Algorithm
- High-dimensional stochastic control models for newsvendor problems and deep learning resolution
- A neural network approach for stochastic optimal control
- Recent developments in machine learning methods for stochastic control and games
- Incomplete information mean-field games and related Riccati equations
- Stochastic optimal control via forward and backward stochastic differential equations and importance sampling
- Stochastic maximum principle for fully coupled nonlinear FBSEs under generalized monotonicity and LQ control applications
- A policy gradient framework for stochastic optimal control problems with global convergence guarantee
- SOC-MartNet: a martingale neural network for the Hamilton-Jacobi-Bellman equation without explicit \(\inf_{u\in U}H\) in stochastic optimal controls
- Convergence of the deep BSDE method for stochastic control problems formulated through the stochastic maximum principle
- Generalized convergence of the deep BSDE method: a step towards fully-coupled FBSDEs and applications in stochastic control
- A deep learning method for solving stochastic optimal control problems driven by fully-coupled FBSDEs
This page was built for publication: Solving stochastic optimal control problem via stochastic maximum principle with deep learning method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2676795)
