Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics

From MaRDI portal
Publication:463893

DOI10.1016/j.automatica.2014.02.015zbMath1417.93134OpenAlexW2013895638MaRDI QIDQ463893

Hamidreza Modares, Mohammad-Bagher Naghibi-Sistani, Bahare Kiumarsi, Ali Karimpour, 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.2014.02.015



Lua error in Module:PublicationMSCList at line 37: attempt to index local 'msc_result' (a nil value).


Related Items (62)

Online data-enabled predictive controlOnline identifier–actor–critic algorithm for optimal control of nonlinear systemsInversion-based output tracking and unknown input reconstruction of square discrete-time linear systemsData-driven optimal tracking control of discrete-time linear systems with multiple delays via the value iteration algorithmNeural-network-based stochastic linear quadratic optimal tracking control scheme for unknown discrete-time systems using adaptive dynamic programmingADP based optimal tracking control for a class of linear discrete-time system with multiple delaysEfficient model-based reinforcement learning for approximate online optimal controlModel-free finite-horizon optimal tracking control of discrete-time linear systemsAn integrated data-driven Markov parameters sequence identification and adaptive dynamic programming method to design fault-tolerant optimal tracking control for completely unknown model systemsData-driven optimal tracking control for discrete-time systems with delays using adaptive dynamic programmingA novel adaptive dynamic programming based on tracking error for nonlinear discrete-time systemsFault-tolerant tracking control based on reinforcement learning with application to a steer-by-wire systemOutput synchronization of heterogeneous discrete-time systems: a model-free optimal approachSimultaneous identification and optimal tracking control of unknown continuous-time systems with actuator constraintsRobust min-max optimal control design for systems with uncertain models: a neural dynamic programming approachStable image representation based stability performance monitoring and recovery for feedback control systemsObserver‐based adaptive controller design for chaos synchronization using Bernstein‐type operatorsOptimal control of unknown discrete-time linear systems with additive noiseRobust optimal tracking control for multiplayer systems by off‐policy Q‐learning approachLearning‐based T‐sHDP() for optimal control of a class of nonlinear discrete‐time systemsModel‐free adaptive tracking control for networked nonlinear systems with data dropoutOutput‐feedback Q‐learning for discrete‐time linear H tracking control: A Stackelberg game approachNonlinear control using human behavior learningModel-free optimal tracking policies for Markov jump systems by solving non-zero-sum gamesOptimal output tracking control of linear discrete-time systems with unknown dynamics by adaptive dynamic programming and output feedbackReinforcement learning and cooperative \(H_\infty\) output regulation of linear continuous-time multi-agent systemsUndiscounted reinforcement learning for infinite-time optimal output tracking and disturbance rejection of discrete-time LTI systems with unknown dynamicsSpecified convergence rate guaranteed output tracking of discrete-time systems via reinforcement learningControl policy learning design for vehicle urban positioning via BeiDou navigationModel-based reinforcement learning for approximate optimal regulationRobust H tracking of linear <scp>discrete‐time</scp> systems using <scp>Q‐learning</scp>Non-zero sum Nash Q-learning for unknown deterministic continuous-time linear systems\(\mathcal{H}_\infty\) tracking learning control for discrete-time Markov jump systems: a parallel off-policy reinforcement learningOptimal tracking control for discrete‐time modal persistent dwell time switched systems based on Q‐learningOptimal trajectory tracking control for a class of nonlinear nonaffine systems via generalized N‐step value gradient learningData‐driven control for networked systems with multiple packet dropoutsFinite‐horizon H∞ tracking control for discrete‐time linear systemsImproved value iteration for nonlinear tracking control with accelerated learningSolution of the linear quadratic regulator problem of black box linear systems using reinforcement learningEvent-triggered optimal tracking control of nonlinear systemsExperience replay–based output feedback Q‐learning scheme for optimal output tracking control of discrete‐time linear systemsReinforcement learning for a class of continuous-time input constrained optimal control problemsOptimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learningA Q-learning predictive control scheme with guaranteed stabilityDiscrete-time dynamical maximum power tracking control for a vertical axis water turbine with retractable bladesData-driven approximate Q-learning stabilization with optimality error bound analysisQ-learning for continuous-time linear systems: A model-free infinite horizon optimal control approachOptimal distributed synchronization control for continuous-time heterogeneous multi-agent differential graphical games\(\mathrm{H}_\infty\) control of linear discrete-time systems: off-policy reinforcement learningPlanning for optimal control and performance certification in nonlinear systems with controlled or uncontrolled switchesLearning output reference model tracking for higher-order nonlinear systems with unknown dynamicsTracking control optimization scheme for a class of partially unknown fuzzy systems by using integral reinforcement learning architectureOnline adaptive policy iteration based fault-tolerant control algorithm for continuous-time nonlinear tracking systems with actuator failuresFinite-horizon optimal tracking guidance for aircraft based on approximate dynamic programmingModel-free \(H_\infty\) tracking control for de-oiling hydrocyclone systems via off-policy reinforcement learningRobust optimal control for finite-horizon zero-sum differential games via a plug-n-play event-triggered schemeOnline optimal and adaptive integral tracking control for varying discrete‐time systems using reinforcement learningOptimal control of a class of nonlinear stochastic systemsAdaptive dynamic programming for model‐free tracking of trajectories with time‐varying parametersMixed density methods for approximate dynamic programmingDissipativity-based verification for autonomous systems in adversarial environmentsComputational intelligence in uncertainty quantification for learning control and differential games



Cites Work


This page was built for publication: Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics