Title :
A pulse neural network learning algorithm for POMDP environment
Author :
Takita, Koichiro ; Hagiwara, Masafumi
Author_Institution :
Fac. of Sci. & Technol., Keio Univ., Yokohama, Japan
fDate :
6/24/1905 12:00:00 AM
Abstract :
In this paper, we propose a new pulse neural network model and its reinforcement learning algorithm. The main purpose of this model is to utilize pulse neurons´ ability to handle sequential inputs in partially observable Markov decision process (POMDP). Its performance is confirmed by computer simulation
Keywords :
Markov processes; decision theory; learning (artificial intelligence); neural nets; POMDP environment; computer simulation; partially observable Markov decision process; pulse neural network learning algorithm; reinforcement learning algorithm; Artificial intelligence; Artificial neural networks; Biological system modeling; Biology computing; Computer networks; Computer simulation; History; Learning; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007764
