Exponential Convergence and Stability of Howard's Policy Improvement Algorithm for Controlled Diffusions

DOI10.1137/19M1236758zbMath1441.93343arXiv1812.07846WikidataQ114978697 ScholiaQ114978697MaRDI QIDQ5111071

Lukasz Szpruch, B. Kerimkulov, David Šiška

Publication date: 26 May 2020

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

Full work available at URL: https://arxiv.org/abs/1812.07846

zbMATH Keywords

stochastic controlbackward stochastic differential equationpolicy improvement algorithm

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Optimal stochastic control (93E20) Exponential stability (93D23)

Related Items

Rates of convergence for the policy iteration method for mean field games systems ⋮ Market based mechanisms for incentivising exchange liquidity provision ⋮ Reinforcement Learning for Linear-Convex Models with Jumps via Stability Analysis of Feedback Controls ⋮ Policy iteration method for time-dependent mean field games systems with non-separable Hamiltonians ⋮ Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems ⋮ A modified MSA for stochastic control problems ⋮ A neural network-based policy iteration algorithm with global \(H^2\)-superlinear convergence for stochastic games on domains ⋮ A policy iteration method for mean field games ⋮ A Modified Method of Successive Approximations for Stochastic Recursive Optimal Control Problems ⋮ Exploratory LQG mean field games with entropy regularization

Cites Work

• Unnamed Item
• Unnamed Item
• Control improvement for jump-diffusion processes with applications to finance
• Markovian quadratic and superquadratic BSDEs with an unbounded terminal condition
• On finite-difference approximations for normalized Bellman equations
• Continuous-time stochastic control and optimization with financial applications
• On the convergence of policy iteration for controlled diffusions
• Infinite horizon backward stochastic differential equations and elliptic equations in Hilbert spaces.
• The rate of convergence of finite-difference approximations for parabolic bellman equations with Lipschitz coefficients in cylindrical domains
• Controlled Markov processes and viscosity solutions
• On the policy improvement algorithm in continuous time
• FUNCTIONAL EQUATIONS IN THE THEORY OF DYNAMIC PROGRAMMING. V. POSITIVITY AND QUASI-LINEARITY
• Some Convergence Results for Howard's Algorithm
• SOME NEW RESULTS IN THE THEORY OF CONTROLLED DIFFUSION PROCESSES
• On the Convergence of Policy Iteration in Stationary Dynamic Programming
• Convergence Properties of Policy Iteration
• Average Optimality in Markov Control Processes via Discounted-Cost Problems and Linear Programming