Title :
An estimate of the number of samples to convergence for critic algorithms
Author_Institution :
DaimlerChrysler AG, Ulm, Germany
Abstract :
Simplified critic based neurocontrol algorithms are analyzed for expected number of samples to convergence. It is shown that there is a fundamental difference in the complexity behavior between the batch and the incremental algorithm, and between the algorithm with and without an explicit plant model. The batch algorithm using a plant model is superior to other variants
Keywords :
computational complexity; convergence of numerical methods; learning (artificial intelligence); neurocontrollers; optimisation; probability; state-space methods; batch algorithm; complexity behavior; convergence; critic algorithms; incremental algorithm; neurocontrol; optimization; probability; state space; Algorithm design and analysis; Convergence; Cost function; Delay effects; Dynamic programming; Neural networks; Probability distribution; Sampling methods; State-space methods; Table lookup;
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.2000.861308
