A study on visual abstraction for reinforcement learning problem using learning vector quantization

Ahmad Afif Mohd Faudzi, Hirotaka Takano, Junichi Murata

研究成果: 会議への寄与タイプ論文

3 引用 (Scopus)

抄録

When applying the learning systems to real-world problems, which have a lot of unknown or uncertain things, there are some issues that need to be solved. One of them is the abstraction ability. In reinforcement learning, to complete each task, the agent will learn to find the best policy. Nevertheless, if a different task is given, we cannot know for sure whether the acquired policy is still valid or not. However, if we can make an abstraction by extract some rules from the policy, it will be easier to understand and possible to apply the policy to different tasks. In this paper, we apply the abstraction at a perceptual level. In the first phase, an action policy is learned using Q-learning, and in the second phase, Learning Vector Quantization is used to extract information out of the learned policy. In this paper, it is verified that by applying the proposed abstraction method, a more useful and simpler representation of the learned policy can be achieved.

元の言語英語
ページ1326-1331
ページ数6
出版物ステータス出版済み - 1 1 2013
イベント2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 - Nagoya, 日本
継続期間: 9 14 20139 17 2013

その他

その他2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013
日本
Nagoya
期間9/14/139/17/13

Fingerprint

Vector quantization
Reinforcement learning
Learning systems

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

これを引用

Faudzi, A. A. M., Takano, H., & Murata, J. (2013). A study on visual abstraction for reinforcement learning problem using learning vector quantization. 1326-1331. 論文発表場所 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, 日本.

A study on visual abstraction for reinforcement learning problem using learning vector quantization. / Faudzi, Ahmad Afif Mohd; Takano, Hirotaka; Murata, Junichi.

2013. 1326-1331 論文発表場所 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, 日本.

研究成果: 会議への寄与タイプ論文

Faudzi, AAM, Takano, H & Murata, J 2013, 'A study on visual abstraction for reinforcement learning problem using learning vector quantization' 論文発表場所 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, 日本, 9/14/13 - 9/17/13, pp. 1326-1331.
Faudzi AAM, Takano H, Murata J. A study on visual abstraction for reinforcement learning problem using learning vector quantization. 2013. 論文発表場所 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, 日本.
Faudzi, Ahmad Afif Mohd ; Takano, Hirotaka ; Murata, Junichi. / A study on visual abstraction for reinforcement learning problem using learning vector quantization. 論文発表場所 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, 日本.6 p.
@conference{7d74ddececb54571a8fea22b70b0b3d3,
title = "A study on visual abstraction for reinforcement learning problem using learning vector quantization",
abstract = "When applying the learning systems to real-world problems, which have a lot of unknown or uncertain things, there are some issues that need to be solved. One of them is the abstraction ability. In reinforcement learning, to complete each task, the agent will learn to find the best policy. Nevertheless, if a different task is given, we cannot know for sure whether the acquired policy is still valid or not. However, if we can make an abstraction by extract some rules from the policy, it will be easier to understand and possible to apply the policy to different tasks. In this paper, we apply the abstraction at a perceptual level. In the first phase, an action policy is learned using Q-learning, and in the second phase, Learning Vector Quantization is used to extract information out of the learned policy. In this paper, it is verified that by applying the proposed abstraction method, a more useful and simpler representation of the learned policy can be achieved.",
author = "Faudzi, {Ahmad Afif Mohd} and Hirotaka Takano and Junichi Murata",
year = "2013",
month = "1",
day = "1",
language = "English",
pages = "1326--1331",
note = "2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 ; Conference date: 14-09-2013 Through 17-09-2013",

}

TY - CONF

T1 - A study on visual abstraction for reinforcement learning problem using learning vector quantization

AU - Faudzi, Ahmad Afif Mohd

AU - Takano, Hirotaka

AU - Murata, Junichi

PY - 2013/1/1

Y1 - 2013/1/1

N2 - When applying the learning systems to real-world problems, which have a lot of unknown or uncertain things, there are some issues that need to be solved. One of them is the abstraction ability. In reinforcement learning, to complete each task, the agent will learn to find the best policy. Nevertheless, if a different task is given, we cannot know for sure whether the acquired policy is still valid or not. However, if we can make an abstraction by extract some rules from the policy, it will be easier to understand and possible to apply the policy to different tasks. In this paper, we apply the abstraction at a perceptual level. In the first phase, an action policy is learned using Q-learning, and in the second phase, Learning Vector Quantization is used to extract information out of the learned policy. In this paper, it is verified that by applying the proposed abstraction method, a more useful and simpler representation of the learned policy can be achieved.

AB - When applying the learning systems to real-world problems, which have a lot of unknown or uncertain things, there are some issues that need to be solved. One of them is the abstraction ability. In reinforcement learning, to complete each task, the agent will learn to find the best policy. Nevertheless, if a different task is given, we cannot know for sure whether the acquired policy is still valid or not. However, if we can make an abstraction by extract some rules from the policy, it will be easier to understand and possible to apply the policy to different tasks. In this paper, we apply the abstraction at a perceptual level. In the first phase, an action policy is learned using Q-learning, and in the second phase, Learning Vector Quantization is used to extract information out of the learned policy. In this paper, it is verified that by applying the proposed abstraction method, a more useful and simpler representation of the learned policy can be achieved.

UR - http://www.scopus.com/inward/record.url?scp=84888606996&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888606996&partnerID=8YFLogxK

M3 - Paper

SP - 1326

EP - 1331

ER -