Title :
Real time reinforcement learning control of dynamic systems applied to an inverted pendulum
Author_Institution :
Dept. of Electr. Eng., Twente Univ., Enschede, Netherlands
Abstract :
Describes work started in order to investigate the use of neural networks for application in adaptive or learning control systems. Neural networks have learning capabilities and they can be used to realize non-linear mappings. These are attractive features which could make them useful building blocks for non-linear adaptive or learning controllers
Keywords :
adaptive systems; learning systems; neural nets; adaptive control systems; dynamic systems; inverted pendulum; learning control systems; learning controllers; neural networks; non-linear mappings; reinforcement learning control;
Conference_Titel :
Symbols Versus Neurons, IEE Colloquium on
Conference_Location :
London
