DocumentCode :
1686274
Title :
Adaptive critic designs for problems with known analytical form of cost function
Author :
Liu, Derong
Author_Institution :
Dept. of Electr. & Comput. Eng., Illinois Univ., Chicago, IL, USA
Volume :
2
fYear :
2002
fDate :
6/24/1905 12:00:00 AM
Firstpage :
1808
Lastpage :
1813
Abstract :
In this paper, we apply adaptive critic designs to a class of failure avoidance control problems. We categorize such problems by the choice of local cost function as zero throughout a trial except at the last time step when a failure occurs. We derive an analytical form of its overall cost function which is defined as the infinite summation of the local cost function over time. We demonstrate that the outputs of the critic network after learning resemble well the analytically derived overall cost function
Keywords :
control system synthesis; discrete time systems; dynamic programming; fault tolerance; learning (artificial intelligence); neurocontrollers; nonlinear dynamical systems; optimal control; robust control; adaptive critic designs; batch learning; cart-pole problem; cost function; critic network; discrete-time system; dynamic programming; failure avoidance control; learning; neural networks; nonlinear dynamical system; optimal control; reinforcement learning; Adaptive control; Buildings; Cost function; Dynamic programming; Failure analysis; Function approximation; Learning; Neural networks; Programmable control; Signal design;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
ISSN :
1098-7576
Print_ISBN :
0-7803-7278-6
Type :
conf
DOI :
10.1109/IJCNN.2002.1007793
Filename :
1007793
Link To Document :
بازگشت