Asymptotic tracking by a reinforcement learning-based adaptive critic controller

• Published in: Journal of control theory and applications Vol. 9; no. 3; pp. 400 - 409
• Main Authors: Bhasin, Shubhendu, Sharma, Nitin, Patre, Parag, Dixon, Warren
• Format: Journal Article
• Language: English
• Published: Heidelberg South China University of Technology and Academy of Mathematics and Systems Science, CAS 01.08.2011; Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL 32611, U.S.A.%Department of Physiology, University of Alberta, Edmonton, Alberta, Canada%NASA Langley Research Center, Hampton, VA 23681, U.S.A
• Subjects: Asymptotic properties; Complexity; Computational Intelligence; Control; Control and Systems Theory; Control systems; Control theory; Disturbances; Engineering; Mechatronics; Neural networks; Nonlinear dynamics; Optimization; Reinforcement; Robotics; Systems Theory; Tracking; Neural network-based control; Adaptive critic; Reinforcement learning
• ISSN: 1672-6340; 1993-0623
• DOI: 10.1007/s11768-011-0170-8

Adaptive critic(AC) based controllers are typically discrete and/or yield a uniformly ultimately bounded stability result because of the presence of disturbances and unknown approximation errors.A continuous-time AC controller is developed that yields asymptotic tracking of a class of uncertain nonlinear systems with bounded disturbances.The proposed AC-based controller consists of two neural networks(NNs)-an action NN,also called the actor,which approximates the plant dynamics and generates appropriate con...