Improved value iteration for neural-network-based stochastic optimal control design

DOI10.1016/j.neunet.2020.01.004zbMath1443.93140OpenAlexW3003653063WikidataQ89611707 ScholiaQ89611707MaRDI QIDQ2185716

Ding Wang, Mingming Liang, Derong Liu

Publication date: 5 June 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2020.01.004

zbMATH Keywords

optimal controlneural networksstochastic processesvalue iterationadaptive dynamic programmingadaptive critic designs

Mathematics Subject Classification ID

Discrete-time control/observation systems (93C55) Dynamic programming (90C39) Optimal stochastic control (93E20) Networked control (93B70)

Related Items

Reinforcement learning for robust stabilization of nonlinear systems with asymmetric saturating actuators ⋮ Optimal control of unknown discrete-time linear systems with additive noise ⋮ Synergetic learning structure-based neuro-optimal fault tolerant control for unknown nonlinear systems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Neural robust stabilization via event-triggering mechanism and adaptive learning technique
• Approximate neural optimal control with reinforcement learning for a torsional pendulum device
• Approximate policy iteration: a survey and some new methods
• Stable Optimal Control and Semicontractive Dynamic Programming
• Proper Policies in Infinite-State Stochastic Shortest Path Problems
• Self-Learning Optimal Regulation for Discrete-Time Nonlinear Systems Under Event-Driven Formulation
• Relaxing Dynamic Programming
• Approximate Dynamic Programming
• Regular Policies in Abstract Dynamic Programming