DocumentCode :
3324423
Title :
Action-dependent adaptive critic designs
Author :
Liu, Derong ; Xiong, Xiaoxu ; Zhang, Yi
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Illinois Univ., Chicago, IL, USA
Volume :
2
fYear :
2001
fDate :
2001
Firstpage :
990
Abstract :
We study a class of action-dependent adaptive critic designs. Conventional adaptive critic designs contain three basic modules: critic, model and action. Each of the three modules can be implemented using a neural network. By combining the critic network and the model network to form a new critic network, we propose a form of action-dependent adaptive critic designs where the critic network implicitly includes a model network in it. An important feature of the present design is that the proposed action-dependent adaptive critic designs can be applied to online learning control applications. We also provide details about the training of the neural networks used in the present design. The training approach described makes it possible the use of many readily available neural network training algorithms and tools without modifications. We employ the pole balancing problem in our simulation study to show the applicability of the present results
Keywords :
control system synthesis; dynamic programming; intelligent control; learning (artificial intelligence); neurocontrollers; optimal control; action-dependent adaptive critic designs; critic network; dynamic programming; learning control; model network; neural network; optimal control; optimisation; pole balancing; Adaptive control; Cost function; Dynamic programming; Equations; Neural networks; Optimal control; Performance analysis; Programmable control; Working environment noise;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
ISSN :
1098-7576
Print_ISBN :
0-7803-7044-9
Type :
conf
DOI :
10.1109/IJCNN.2001.939495
Filename :
939495
Link To Document :
بازگشت