Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems

DOI10.1016/j.automatica.2013.09.043zbMath1298.49042MaRDI QIDQ463819

Mohammad-Bagher Naghibi-Sistani, Hamidreza Modares, Frank L. Lewis

Publication date: 17 October 2014

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2013.09.043

zbMATH Keywords

optimal control; neural networks; input constraints; integral reinforcement learning; experience replay

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

49L20: Dynamic programming in optimal control and differential games

92B20: Neural networks for/in biological studies, artificial life and related topics

93C40: Adaptive control/observation systems

Related Items

Finite-horizon differential games for missile–target interception system using adaptive dynamic programming with input constraints, Online optimal and adaptive integral tracking control for varying discrete‐time systems using reinforcement learning, A new information-weighted recursive algorithm for time-varying systems: application to UAV system identification, Finite-horizon optimal control for continuous-time uncertain nonlinear systems using reinforcement learning, Simultaneous identification and optimal tracking control of unknown continuous-time systems with actuator constraints, Experience replay–based output feedback Q‐learning scheme for optimal output tracking control of discrete‐time linear systems, Modified value-function-approximation for synchronous policy iteration with single-critic configuration for nonlinear optimal control, Open‐loop Stackelberg learning solution for hierarchical control problems, Decentralised zero-sum differential game for a class of large-scale interconnected systems via adaptive dynamic programming, Recursive estimation in piecewise affine systems using parameter identifiers and concurrent learning, Online concurrent reinforcement learning algorithm to solve two‐player zero‐sum games for partially unknown nonlinear continuous‐time systems, Off‐policy integral reinforcement learning‐based optimal tracking control for a class of nonzero‐sum game systems with unknown dynamics, A New Integral Critic Learning for Optimal Tracking Control with Applications to Boiler‐Turbine Systems, Adaptive neural optimal tracking control of stochastic nonstrict-feedback nonlinear systems with output constraints, Finite-time prescribed performance optimal attitude control for quadrotor UAV, Continuous‐time receding‐horizon reinforcement learning and its application to path‐tracking control of autonomous ground vehicles, Optimal event‐triggered control for C‐T system with asymmetric constraints based on dual heuristic dynamic programing structure, Reinforcement learning‐based optimized backstepping control for strict‐feedback nonlinear systems subject to external disturbances, Optimal consensus control for double‐integrator multiagent systems with unknown dynamics using adaptive dynamic programming, Efficient model-based reinforcement learning for approximate online optimal control, Optimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learning, Neural-network-based robust optimal control design for a class of uncertain nonlinear systems via adaptive dynamic programming, Optimal adaptive fuzzy FTC design for strict-feedback nonlinear uncertain systems with actuator faults, Model-based reinforcement learning for approximate optimal regulation, Backstepping-based adaptive dynamic programming for missile-target guidance systems with state and input constraints, General value iteration based single network approach for constrained optimal controller design of partially-unknown continuous-time nonlinear systems, Reinforcement learning solution for HJB equation arising in constrained optimal control problem, Reinforcement learning for a class of continuous-time input constrained optimal control problems, Neural network based central heating system load prediction and constrained control, Multiple model adaptive tracking control based on adaptive dynamic programming, A model for system uncertainty in reinforcement learning, Optimal distributed synchronization control for continuous-time heterogeneous multi-agent differential graphical games, Online approximate solution of HJI equation for unknown constrained-input nonlinear continuous-time systems, Data-based reinforcement learning approximate optimal control for an uncertain nonlinear system with control effectiveness faults, Integral reinforcement learning based event-triggered control with input saturation, Model-free \(H_\infty\) tracking control for de-oiling hydrocyclone systems via off-policy reinforcement learning, Reinforcement learning for distributed control and multi-player games, Mixed density methods for approximate dynamic programming, Adaptive dynamic programming in the Hamiltonian-driven framework, Dissipativity-based verification for autonomous systems in adversarial environments, Self-learning robust optimal control for continuous-time nonlinear systems with mismatched disturbances, Robust min-max optimal control design for systems with uncertain models: a neural dynamic programming approach, Reinforcement learning for robust adaptive control of partially unknown nonlinear systems subject to unmatched uncertainties, Data-based robust adaptive control for a class of unknown nonlinear constrained-input systems via integral reinforcement learning, Adaptive cruise control via adaptive dynamic programming with experience replay, Event-triggered distributed self-learning robust tracking control for uncertain nonlinear interconnected systems, A novel adaptive dynamic programming based on tracking error for nonlinear discrete-time systems, Model-FreeH_∞Control Design for Unknown Continuous-Time Linear System Using Adaptive Dynamic Programming, Approximate optimal adaptive control for weakly coupled nonlinear systems: A neuro-inspired approach, Optimal control of a class of nonlinear stochastic systems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems
• Stochastic optimal control of unknown linear networked control system in the presence of random delays and packet losses
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• Adaptive optimal control for continuous-time linear systems based on policy iteration
• Real-time reinforcement learning by sequential actor-critics and experience replay
• A novel actor-critic-identifier architecture for approximate optimal control of uncertain nonlinear systems
• Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach
• Approximate Dynamic Programming
• Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers