Linear Quadratic Tracking Control of Partially-Unknown Continuous-Time Systems Using Reinforcement Learning

DOI10.1109/TAC.2014.2317301zbMath1360.93726OpenAlexW1972243698MaRDI QIDQ2982965

Hamidreza Modares, Frank L. Lewis

Publication date: 16 May 2017

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tac.2014.2317301

Mathematics Subject Classification ID

Identification in stochastic control theory (93E12) Linear-quadratic optimal control problems (49N10)

Related Items

Heterogeneous formation control of multiple rotorcrafts with unknown dynamics by reinforcement learning, Reinforcement learning explains various conditional cooperation, Optimal model-free output synchronization of heterogeneous systems using off-policy reinforcement learning, Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design, An integrated data-driven Markov parameters sequence identification and adaptive dynamic programming method to design fault-tolerant optimal tracking control for completely unknown model systems, Data-driven optimal tracking control for discrete-time systems with delays using adaptive dynamic programming, Reinforcement learning solution for HJB equation arising in constrained optimal control problem, Policy iterations for reinforcement learning problems in continuous time and space -- fundamental theory and methods, Fault-tolerant tracking control based on reinforcement learning with application to a steer-by-wire system, Online barrier-actor-critic learning for \(H_\infty\) control with full-state constraints and input saturation, Reinforcement learning‐based adaptive optimal tracking algorithm for Markov jump systems with partial unknown dynamics, Off‐policy integral reinforcement learning‐based optimal tracking control for a class of nonzero‐sum game systems with unknown dynamics, Guaranteed cost fault-tolerant control for uncertain stochastic systems via dynamic event-triggered adaptive dynamic programming, State feedback control for stochastic regular linear quadratic tracking problem with input time delay, Learning‐based T‐sHDP() for optimal control of a class of nonlinear discrete‐time systems, Optimal robust formation control for heterogeneous multi‐agent systems based on reinforcement learning, Output‐feedback Q‐learning for discrete‐time linear H^∞ tracking control: A Stackelberg game approach, Nonlinear control using human behavior learning, Optimal output tracking control of linear discrete-time systems with unknown dynamics by adaptive dynamic programming and output feedback, Linear quadratic tracking control of unknown systems: a two-phase reinforcement learning method, Undiscounted reinforcement learning for infinite-time optimal output tracking and disturbance rejection of discrete-time LTI systems with unknown dynamics, Data-driven optimal tracking control of switched linear systems, Specified convergence rate guaranteed output tracking of discrete-time systems via reinforcement learning, Robust H_∞ tracking of linear <scp>discrete‐time</scp> systems using <scp>Q‐learning</scp>, Data-driven optimal control via linear transfer operators: a convex approach, \(\mathcal{H}_\infty\) tracking learning control for discrete-time Markov jump systems: a parallel off-policy reinforcement learning, Optimal tracking control for discrete‐time modal persistent dwell time switched systems based on Q‐learning, Finite‐horizon H∞ tracking control for discrete‐time linear systems, ADP‐based robust consensus for multi‐agent systems with unknown dynamics and random uncertain channels, Solution of the linear quadratic regulator problem of black box linear systems using reinforcement learning, Event-triggered optimal tracking control of nonlinear systems, Off-policy learning for adaptive optimal output synchronization of heterogeneous multi-agent systems, Experience replay–based output feedback Q‐learning scheme for optimal output tracking control of discrete‐time linear systems, Optimal adaptive control of drug dosing using integral reinforcement learning, Data-based and secure switched cyber-physical systems, Event-triggered single-network ADP method for constrained optimal tracking control of continuous-time non-linear systems, Tracking control optimization scheme for a class of partially unknown fuzzy systems by using integral reinforcement learning architecture, Output regulation of unknown linear systems using average cost reinforcement learning, Stackelberg games for model-free continuous-time stochastic systems based on adaptive dynamic programming, Online adaptive policy iteration based fault-tolerant control algorithm for continuous-time nonlinear tracking systems with actuator failures, Output‐feedback H_∞ quadratic tracking control of linear systems using reinforcement learning, Off-policy Q-learning: solving Nash equilibrium of multi-player games with network-induced delay and unmeasured state, Online optimal and adaptive integral tracking control for varying discrete‐time systems using reinforcement learning, Adaptive dynamic programming for model‐free tracking of trajectories with time‐varying parameters, Output synchronization control for a class of complex dynamical networks with non-identical dynamics, Reinforcement learning for distributed control and multi-player games, Adaptive optimal output tracking of continuous-time systems via output-feedback-based reinforcement learning