Deep Learning Approximation for Stochastic Control Problems

Abstract

Many real world stochastic control problems suffer from the "curse of dimensionality". To overcome this difficulty, we develop a deep learning approach that directly solves high-dimensional stochastic control problems based on Monte-Carlo sampling. We approximate the time-dependent controls as feedforward neural networks and stack these networks together through model dynamics. The objective function for the control problem plays the role of the loss function for the deep neural network. We test this approach using examples from the areas of optimal trading and energy storage. Our results suggest that the algorithm presented here achieves satisfactory accuracy and at the same time, can handle rather high dimensional problems.

Cited by in corpus (14)

• Multi-scale Deep Neural Networks for Solving High Dimensional PDEs
• Neural networks-based algorithms for stochastic control and PDEs in finance
• Reinforcement Learning via Parametric Cost Function Approximation for Multistage Stochastic Programming
• Signatured Deep Fictitious Play for Mean Field Games with Common Noise
• Deep Forward-Backward SDEs for Min-max Control
• Deep Learning for Mean Field Games and Mean Field Control with Applications to Finance
• Deep neural network for optimal retirement consumption in defined contribution pension system
• Neural Network Approximations of Compositional Functions With Applications to Dynamical Systems
• Deep Learning Based Online Power Control for Large Energy Harvesting Networks
• Machine Learning and Control Theory
• A Two-Part Controller Synthesis Approach for Nonlinear Stochastic Systems Perturbed by Lévy Noise Using Renewal Theory and HJB-Based Impulse Control
• Meshfree Approximation for Stochastic Optimal Control Problems
• Deep Semi-Martingale Optimal Transport
• Approximate policy iteration using neural networks for storage problems