封面圖片

Effectiveness of a recurrent neural network in emergence of discrete decision making through reinforcement learning

The 2nd International Malaysia-Ireland Joint Symposium on Engineering, Science and Business 2012 (IMiEJS2012) jointly organized by Universiti Malaysia Perlis and Athlone Institute of Technology in collaboration with The Ministry of Higher Education (MOHE) Malaysia, Education Malaysia and Malaysia Po...

全面介紹

Saved in:
書目詳細資料
Main Authors: Mohamad Faizal, Samsudin, Hazry, Desa, Dr., Shibata, Katsunari
其他作者: faizalsamsudin@unimap.edu.my
格式: Working Paper
語言:English
出版: Universiti Malaysia Perlis (UniMAP) 2013
主題:
Recurrent neural network
Localized inputs
Continuous-state space
Discrete space representation
在線閱讀:http://dspace.unimap.edu.my/xmlui/handle/123456789/29026
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
id my.unimap-29026
record_format dspace
spelling my.unimap-290262013-10-21T07:33:33Z Effectiveness of a recurrent neural network in emergence of discrete decision making through reinforcement learning Mohamad Faizal, Samsudin Hazry, Desa, Dr. Shibata, Katsunari faizalsamsudin@unimap.edu.my hazry@unimap.edu.my Recurrent neural network Localized inputs Continuous-state space Discrete space representation The 2nd International Malaysia-Ireland Joint Symposium on Engineering, Science and Business 2012 (IMiEJS2012) jointly organized by Universiti Malaysia Perlis and Athlone Institute of Technology in collaboration with The Ministry of Higher Education (MOHE) Malaysia, Education Malaysia and Malaysia Postgraduates Student Association Ireland (MyPSI), 18th - 19th June 2012 at Putra World Trade Center (PWTC), Kuala Lumpur, Malaysia. In a discrete decision making task, using a neural network suffers from the problem of discrete decision making. On the other hand, using a lookup table suffers from the problem in generalization and the curse of dimensionality. To overcome this problem, simple localized inputs in neural network are used. Furthermore, this paper focus on examining whether by utilizing the internal dynamics in RNN, quick decision making can be obtained through learning or not. In this paper, it is shown that a robot learned to make a discrete decision making even though no special technique other than a localized inputs in RNN through RL was utilized. 2013-10-21T07:33:33Z 2013-10-21T07:33:33Z 2012-06-18 Working Paper p. 459-465 978-967-5760-11-2 http://hdl.handle.net/123456789/29026 en Proceedings of the The 2nd International Malaysia-Ireland Joint Symposium on Engineering, Science and Business 2012 (IMiEJS2012); Universiti Malaysia Perlis (UniMAP)
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Recurrent neural network
Localized inputs
Continuous-state space
Discrete space representation
spellingShingle Recurrent neural network
Localized inputs
Continuous-state space
Discrete space representation
Mohamad Faizal, Samsudin
Hazry, Desa, Dr.
Shibata, Katsunari
Effectiveness of a recurrent neural network in emergence of discrete decision making through reinforcement learning
description The 2nd International Malaysia-Ireland Joint Symposium on Engineering, Science and Business 2012 (IMiEJS2012) jointly organized by Universiti Malaysia Perlis and Athlone Institute of Technology in collaboration with The Ministry of Higher Education (MOHE) Malaysia, Education Malaysia and Malaysia Postgraduates Student Association Ireland (MyPSI), 18th - 19th June 2012 at Putra World Trade Center (PWTC), Kuala Lumpur, Malaysia.
author2 faizalsamsudin@unimap.edu.my
author_facet faizalsamsudin@unimap.edu.my
Mohamad Faizal, Samsudin
Hazry, Desa, Dr.
Shibata, Katsunari
format Working Paper
author Mohamad Faizal, Samsudin
Hazry, Desa, Dr.
Shibata, Katsunari
author_sort Mohamad Faizal, Samsudin
title Effectiveness of a recurrent neural network in emergence of discrete decision making through reinforcement learning
title_short Effectiveness of a recurrent neural network in emergence of discrete decision making through reinforcement learning
title_full Effectiveness of a recurrent neural network in emergence of discrete decision making through reinforcement learning
title_fullStr Effectiveness of a recurrent neural network in emergence of discrete decision making through reinforcement learning
title_full_unstemmed Effectiveness of a recurrent neural network in emergence of discrete decision making through reinforcement learning
title_sort effectiveness of a recurrent neural network in emergence of discrete decision making through reinforcement learning
publisher Universiti Malaysia Perlis (UniMAP)
publishDate 2013
url http://dspace.unimap.edu.my/xmlui/handle/123456789/29026
_version_ 1643795572821327872
score 13.250246

相似書籍