A set-based model-free reinforcement learning design technique for nonlinear systems
- 8 October 2018
- journal article
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 51 (18) , 37-42
Abstract
No abstract availableKeywords
This publication has 10 references indexed in Scilit:
- Extremum seeking control based on phasor estimationSystems & Control Letters, 2015
- Adaptive Estimation for a Class of Nonlinearly Parameterized Dynamical SystemsIEEE Transactions on Automatic Control, 2014
- A novel actor–critic–identifier architecture for approximate optimal control of uncertain nonlinear systemsAutomatica, 2013
- Online actor–critic algorithm to solve the continuous-time infinite horizon optimal control problemAutomatica, 2010
- Q-learning and Pontryagin's Minimum Principle2009
- Adaptive linear quadratic control using policy iteration2005
- Neuro-dynamic programming: an overview2002
- Q-learningMachine Learning, 1992
- Reinforcement learning is direct adaptive optimal controlIEEE Control Systems, 1992
- Neuronlike adaptive elements that can solve difficult learning control problemsIEEE Transactions on Systems, Man, and Cybernetics, 1983