Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications

DOI10.1007/s11009-019-09767-9zbMath1496.93112arXiv1812.05916OpenAlexW3016378723MaRDI QIDQ2671220

Achref Bachouch, Huyên Pham, Côme Huré, Nicolas Langrené

Publication date: 3 June 2022

Published in: Methodology and Computing in Applied Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1812.05916

zbMATH Keywords

Monte Carloquantizationvalue iterationdeep learningpolicy learningperformance iteration

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Discrete-time control/observation systems (93C55) Stochastic systems in control theory (general) (93E03)

Related Items (17)

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 ⋮ Value-Gradient Based Formulation of Optimal Control Problem and Machine Learning Algorithm ⋮ Overcoming the timescale barrier in molecular dynamics: Transfer operators, variational principles and machine learning ⋮ Deep empirical risk minimization in finance: Looking into the future ⋮ 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 ⋮ Optimal liquidation through a limit order book: a neural network and simulation approach ⋮ Performance of a Markovian neural network versus dynamic programming on a fishing control problem ⋮ Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis ⋮ An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations ⋮ Deep combinatorial optimisation for optimal stopping time problems: application to swing options pricing. ⋮ Automatic model training under restrictive time constraints

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Numerical simulation of quadratic BSDEs
• Numerical simulation of BSDEs with drivers of quadratic growth
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Machine learning for semi linear PDEs
• An Approximate Dynamic Programming Algorithm for Monotone Value Functions
• Valuation of energy storage: an optimal switching approach
• Hedging Derivative Securities and Incomplete Markets: An ε-Arbitrage Approach
• Regression Monte Carlo for microgrid management
• A class of finite-dimensional numerically solvable McKean-Vlasov control problems
• Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications