Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems

DOI10.1137/22m1492180arXiv2203.11758OpenAlexW4389301972MaRDI QIDQ6140987

Christoph Reisinger, Yu-Fei Zhang, Wolfgang Stockinger

Publication date: 2 January 2024

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.11758

zbMATH Keywords

stochastic controllinear convergencebackward stochastic differential equationstationary pointreinforcement learningpolicy gradient method

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Numerical methods based on necessary conditions (49M05) Optimal stochastic control (93E20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Sufficient stochastic maximum principle for discounted control problem
• Time discretization of FBSDE with polynomial growth drivers and reaction-diffusion PDEs
• Continuous-time stochastic control and optimization with financial applications
• Nonlinear control systems: An introduction
• Introductory lectures on convex optimization. A basic course.
• BSDEs with polynomial growth generators
• A neural network-based policy iteration algorithm with global \(H^2\)-superlinear convergence for stochastic games on domains
• A modified MSA for stochastic control problems
• Time discretization and Markovian iteration for coupled FBSDEs
• A regression-based Monte Carlo method to solve backward stochastic differential equations
• Convexity and Optimization in Banach Spaces
• Variational Analysis
• On the convergence rate of approximation schemes for Hamilton-Jacobi-Bellman Equations
• A Numerical Scheme for a Mean Field Game in Some Queueing Systems Based on Markov Chain Approximation Method
• Deep backward schemes for high-dimensional nonlinear PDEs
• Solving high-dimensional partial differential equations using deep learning
• Exponential Convergence and Stability of Howard's Policy Improvement Algorithm for Controlled Diffusions
• Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
• Backward Stochastic Differential Equations
• Mean Field Games and Mean Field Type Control Theory

This page was built for publication: Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems