Title :
Online learning control by association and reinforcement
Author :
Si, Jennie ; Wang, Yu-tsung
Author_Institution :
Dept. of Electr. Eng., Arizona State Univ., Tempe, AZ, USA
Abstract :
This paper focuses on a systematic treatment for developing a generic online learning control system based on the fundamental principle of reinforcement learning or more specifically neuro-dynamic programming. This real time learning system improves its performance over time in two aspects: it learns from its own mistakes through the reinforcement signal from the external environment and try to reinforce its action to improve future performance; and system´s state associated with the positive reinforcement is memorized through a network learning process where in the future, similar states will be more positively associated with a control action leading to a positive reinforcement. Two successful candidates of online learning control designs are introduced. Real time learning algorithms can be derived for individual components in the learning system. Some analytical insights are provided to give some guidelines on the entire online learning control system
Keywords :
dynamic programming; learning (artificial intelligence); neurocontrollers; real-time systems; self-organising feature maps; adaptive critic network; learning by association; neural nets; neural-dynamic programming; online learning control; real time system; reinforcement learning; self organising map; Control design; Control systems; Dynamic programming; Guidelines; Learning systems; Optimal control; Real time systems; System performance; System testing; Velocity measurement;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.861307