Reinforcement learning control for a robotic manipulator with unknown deadzone
Authors:
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 593-598
Abstract
In this paper, an actor critic neural network control is developed for a robotic manipulator. Both system uncertainties and unknown deadzone are considered in the tracking control design. Stability of the closed-loop system is analyzed via the Lyapunov's direct method. The critic neural network is used to estimate the cost-to-go and the actor neural network is used to make the cost-to-go converge. Simulation studies are conducted to examine the effectiveness of the proposed actor critic neural network control.Keywords
This publication has 13 references indexed in Scilit:
- Online actor–critic algorithm to solve the continuous-time infinite horizon optimal control problemAutomatica, 2010
- Reinforcement learning and adaptive dynamic programming for feedback controlIEEE Circuits and Systems Magazine, 2009
- Adaptive optimal control for continuous-time linear systems based on policy iterationAutomatica, 2009
- Adaptive optimal control algorithm for continuous-time nonlinear systems based on policy iteration2008
- Adaptive neural control of MIMO nonlinear state time-varying delay systems with unknown dead-zones and gain signsAutomatica, 2007
- Adaptive Neural Control of Uncertain MIMO Nonlinear SystemsIEEE Transactions on Neural Networks, 2004
- Intelligent compensation of actuator nonlinearities2004
- Adaptive NN control of uncertain nonlinear pure-feedback systemsAutomatica, 2002
- Online learning control by association and reinforcementIEEE Transactions on Neural Networks, 2001
- Reinforcement Learning in Continuous Time and SpaceNeural Computation, 2000