Temporal difference-based policy iteration for optimal control of stochastic systems

DOI10.1007/s10957-013-0418-1zbMath1306.93074OpenAlexW2080453320MaRDI QIDQ467477

Xiao-Mei Liu, Kang Cheng, Kanjian Zhang, Haikun Wei, Shu-Min Fei

Publication date: 3 November 2014

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10957-013-0418-1

zbMATH Keywords

stochastic optimal controlapproximate dynamic programminglearning algorithms: discrete-time systemsleast squares policy evaluation algorithm

Mathematics Subject Classification ID

Dynamic programming in optimal control and differential games (49L20) Discrete-time control/observation systems (93C55) Dynamic programming (90C39) Optimal stochastic control (93E20) Stochastic systems in control theory (general) (93E03) Existence of optimal solutions to problems involving randomness (49J55)

Related Items (2)

Potential-based least-squares policy iteration for a parameterized feedback control system ⋮ Suboptimal control for nonlinear systems with disturbance via integral sliding mode control and policy iteration

Cites Work

• Unnamed Item
• Unnamed Item
• Stochastic control via direct comparison
• Markov chains and stochastic stability
• A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases
• Projected equation methods for approximate solution of large linear systems
• Single sample path-based optimization of Markov chains
• Least squares policy evaluation algorithms with linear function approximation
• Linear least-squares algorithms for temporal difference learning
• A unified approach to Markov decision problems and performance sensitivity analysis
• Policy iteration based feedback control
• Approximate policy iteration: a survey and some new methods
• A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications
• On the use of the deterministic Lyapunov function for the ergodicity of stochastic difference equations
• An analysis of temporal-difference learning with function approximation
• Perturbation realization, potentials, and sensitivity analysis of Markov processes
• 10.1162/1532443041827907
• Convergence Results for Some Temporal Difference Methods Based on Least Squares
• Potential-Based Online Policy Iteration Algorithms for Markov Decision Processes
• Approximate Dynamic Programming

This page was built for publication: Temporal difference-based policy iteration for optimal control of stochastic systems