Title :
An Improved Minibrain That Learns Through Both Positive and Negative Feedback
Author :
Wee Phua, Chee ; Blair, Alan
Author_Institution :
Univ. of New South Wales, Sydney
Abstract :
A new reinforcement learned neural network, that follows the ideas of the minibrain network but includes exploration and learns through both positive and negative feedback, is proposed. The proposed ReL network is evaluated against the minibrain network in the n times n grid world domain and the taxi domain and is shown to perform significantly better than the minibrain network.
Keywords :
feedback; learning (artificial intelligence); neural nets; ReL network; minibrain; negative feedback; positive feedback; reinforcement learned neural network; Biological neural networks; Biological system modeling; Brain modeling; Learning; Negative feedback; Neural networks; Parallel processing; Performance evaluation; Road vehicles; Vehicle driving;
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
DOI :
10.1109/IJCNN.2006.246768
