A pulse neural network learning algorithm for POMDP environment

Koichiro Takita, Masafumi Hagiwara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In this paper, we proposed a new pulse neural network model and its reinforcement learning algorithm. The main purpose of this model is to utilize pulse neuron's ability to handle sequential inputs in partially observable Markov decision process (POMDP). Its performance is confirmed by computer simulation.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages1643-1648
Number of pages6
Volume2
Publication statusPublished - 2002
Event2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States
Duration: 2002 May 122002 May 17

Other

Other2002 International Joint Conference on Neural Networks (IJCNN '02)
CountryUnited States
CityHonolulu, HI
Period02/5/1202/5/17

Fingerprint

Learning algorithms
Neural networks
Reinforcement learning
Neurons
Computer simulation

Keywords

  • Pulse neural network
  • Reinforcement learning

ASJC Scopus subject areas

  • Software

Cite this

Takita, K., & Hagiwara, M. (2002). A pulse neural network learning algorithm for POMDP environment. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 1643-1648)

A pulse neural network learning algorithm for POMDP environment. / Takita, Koichiro; Hagiwara, Masafumi.

Proceedings of the International Joint Conference on Neural Networks. Vol. 2 2002. p. 1643-1648.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Takita, K & Hagiwara, M 2002, A pulse neural network learning algorithm for POMDP environment. in Proceedings of the International Joint Conference on Neural Networks. vol. 2, pp. 1643-1648, 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States, 02/5/12.
Takita K, Hagiwara M. A pulse neural network learning algorithm for POMDP environment. In Proceedings of the International Joint Conference on Neural Networks. Vol. 2. 2002. p. 1643-1648
Takita, Koichiro ; Hagiwara, Masafumi. / A pulse neural network learning algorithm for POMDP environment. Proceedings of the International Joint Conference on Neural Networks. Vol. 2 2002. pp. 1643-1648
@inproceedings{25a36944bd9c496fa2a975edd0530e4e,
title = "A pulse neural network learning algorithm for POMDP environment",
abstract = "In this paper, we proposed a new pulse neural network model and its reinforcement learning algorithm. The main purpose of this model is to utilize pulse neuron's ability to handle sequential inputs in partially observable Markov decision process (POMDP). Its performance is confirmed by computer simulation.",
keywords = "Pulse neural network, Reinforcement learning",
author = "Koichiro Takita and Masafumi Hagiwara",
year = "2002",
language = "English",
volume = "2",
pages = "1643--1648",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - A pulse neural network learning algorithm for POMDP environment

AU - Takita, Koichiro

AU - Hagiwara, Masafumi

PY - 2002

Y1 - 2002

N2 - In this paper, we proposed a new pulse neural network model and its reinforcement learning algorithm. The main purpose of this model is to utilize pulse neuron's ability to handle sequential inputs in partially observable Markov decision process (POMDP). Its performance is confirmed by computer simulation.

AB - In this paper, we proposed a new pulse neural network model and its reinforcement learning algorithm. The main purpose of this model is to utilize pulse neuron's ability to handle sequential inputs in partially observable Markov decision process (POMDP). Its performance is confirmed by computer simulation.

KW - Pulse neural network

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=0036083221&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036083221&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0036083221

VL - 2

SP - 1643

EP - 1648

BT - Proceedings of the International Joint Conference on Neural Networks

ER -