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 2013 → 9 17 2013 |
その他
その他 | 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 |
---|---|
国 | 日本 |
市 | Nagoya |
期間 | 9/14/13 → 9/17/13 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Computer Science Applications
- Electrical and Electronic Engineering
これを引用
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
}
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
AN - SCOPUS:84888606996
SP - 1326
EP - 1331
ER -