Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis
From MaRDI portal
Publication:5151934
DOI10.1137/20M1316640zbMath1466.65007arXiv1812.04300OpenAlexW2903857590MaRDI QIDQ5151934
Achref Bachouch, Nicolas Langrené, Côme Huré, Huyên Pham
Publication date: 23 February 2021
Published in: SIAM Journal on Numerical Analysis (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1812.04300
Monte Carlo methods (65C05) Dynamic programming (90C39) Stochastic learning and adaptive control (93E35) Neural nets and related approaches to inference from stochastic processes (62M45)
Related Items (31)
Robust utility maximization under model uncertainty via a penalization approach ⋮ An Algorithm to Construct Subsolutions of Convex Optimal Control Problems ⋮ Discrete-Time Portfolio Optimization under Maximum Drawdown Constraint with Partial Information and Deep Learning Resolution ⋮ Error Estimates for a Tree Structure Algorithm Solving Finite Horizon Control Problems ⋮ SympOCnet: Solving Optimal Control Problems with Applications to High-Dimensional Multiagent Path Planning Problems ⋮ Deep learning for constrained utility maximisation ⋮ Full error analysis for the training of deep neural networks ⋮ Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications ⋮ Value-Gradient Based Formulation of Optimal Control Problem and Machine Learning Algorithm ⋮ Finite Horizon Impulse control of Stochastic Functional Differential Equations ⋮ Overcoming the timescale barrier in molecular dynamics: Transfer operators, variational principles and machine learning ⋮ Solving stochastic optimal control problem via stochastic maximum principle with deep learning method ⋮ Deep empirical risk minimization in finance: Looking into the future ⋮ Event-triggered fault-tolerant control for input-constrained nonlinear systems with mismatched disturbances via adaptive dynamic programming ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ Optimal polynomial feedback laws for finite horizon control problems ⋮ Neural networks for first order HJB equations and application to front propagation with obstacle terms ⋮ Deep reinforcement learning in finite-horizon to explore the most probable transition pathway ⋮ Numerical resolution of McKean-Vlasov FBSDEs using neural networks ⋮ A Normalizing Field Flow Induced Two-Stage Stochastic Homogenization Method for Random Composite Materials ⋮ Beating a Benchmark: Dynamic Programming May Not Be the Right Numerical Approach ⋮ Optimal liquidation through a limit order book: a neural network and simulation approach ⋮ Optimal Market Making with Persistent Order Flow ⋮ A Machine Learning Approach to Adaptive Robust Utility Maximization and Hedging ⋮ A neural network-based policy iteration algorithm with global \(H^2\)-superlinear convergence for stochastic games on domains ⋮ A deep learning model for gas storage optimization ⋮ Polynomial affine approach to HARA utility maximization with applications to OrnsteinUhlenbeck \(4/2\) models. ⋮ Adaptive Deep Learning for High-Dimensional Hamilton--Jacobi--Bellman Equations ⋮ Deep combinatorial optimisation for optimal stopping time problems: application to swing options pricing. ⋮ Approximation Error Analysis of Some Deep Backward Schemes for Nonlinear PDEs ⋮ Automatic model training under restrictive time constraints
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- A distribution-free theory of nonparametric regression
- Convergence of the deep BSDE method for coupled FBSDEs
- Nonparametric regression with additional measurement errors in the dependent variable
- Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications
- Approximate Dynamic Programming
- PRICING OF HIGH-DIMENSIONAL AMERICAN OPTIONS BY NEURAL NETWORKS
- Breaking the Curse of Dimensionality with Convex Neural Networks
- Valuing American Options by Simulation: A Simple Least-Squares Approach
- Approximation by superpositions of a sigmoidal function
This page was built for publication: Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis
