Online reinforcement learning for a class of partially unknown continuous-time nonlinear systems via value iteration

DOI10.1002/OCA.2391MaRDI QIDQ3176482zbMATHOpenAlexFDO

Authors Hanguang Su, Huaguang Zhang, Kun Zhang, Wenzhong Gao

Publication date 20 July 2018

Published in Optimal Control Applications \& Methods (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/oca.2391

zbMATH Keywords

value iterationonline learningcontinuous-time systemsapproximation dynamic programming (ADP)integral reinforcement learning (IRL)

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Dynamic programming (90C39) Nonlinear systems in control theory (93C10) Control/observation systems governed by ordinary differential equations (93C15) Control/observation systems with incomplete information (93C41)

Recommendations

• General value iteration based single network approach for constrained optimal controller design of partially-unknown continuous-time nonlinear systems
• Online adaptive algorithm for with integral reinforcement learning
• Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems
• Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning
• Neuro-optimal tracking control for a class of discrete-time nonlinear systems via generalized value iteration adaptive dynamic programming approach

Cited in

(12)

• Modified value-function-approximation for synchronous policy iteration with single-critic configuration for nonlinear optimal control
• General value iteration based single network approach for constrained optimal controller design of partially-unknown continuous-time nonlinear systems
• Off‐policy integral reinforcement learning‐based optimal tracking control for a class of nonzero‐sum game systems with unknown dynamics
• Adaptive optimal control of continuous-time nonlinear affine systems via hybrid iteration
• Multi-event-triggered adaptive dynamic programming for non-zero-sum game of unknown nonlinear system
• Distributed optimal control of nonlinear multi-agent systems based on integral reinforcement learning
• A stabilizing reinforcement learning approach for sampled systems with partially unknown models
• Adaptive dynamic programming for decentralized neuro‐control of nonlinear systems subject to mismatched interconnections
• Model‐free optimal tracking over finite horizon using adaptive dynamic programming
• A novel optimal control design for unknown nonlinear systems based on adaptive dynamic programming and nonlinear model predictive control
• Optimal control for continuous-time Markov jump singularly perturbed systems: a hybrid reinforcement learning scheme
• Neighbor Q‐learning based consensus control for discrete‐time multi‐agent systems

This page was built for publication: Online reinforcement learning for a class of partially unknown continuous-time nonlinear systems via value iteration

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3176482)