A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization

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. Neverthele...

Full description

Bibliographic Details
Main Authors:	Ahmad Afif, Mohd Faudzi, Hirotaka, Takano, Junichi, Murata
Format:	Conference or Workshop Item
Language:	English
Published:	2013
Subjects:	TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://umpir.ump.edu.my/id/eprint/6961/ http://umpir.ump.edu.my/id/eprint/6961/1/A_study_on_Visual_Abstraction_for_Reinforcement_Learning_Problem_Using_Learning_Vector_Quantization.pdf

id	ump-6961
recordtype	eprints
spelling	ump-69612015-03-03T09:33:29Z http://umpir.ump.edu.my/id/eprint/6961/ A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization Ahmad Afif, Mohd Faudzi Hirotaka, Takano Junichi, Murata TK Electrical engineering. Electronics Nuclear engineering 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. 2013 Conference or Workshop Item PeerReviewed application/pdf en http://umpir.ump.edu.my/id/eprint/6961/1/A_study_on_Visual_Abstraction_for_Reinforcement_Learning_Problem_Using_Learning_Vector_Quantization.pdf Ahmad Afif, Mohd Faudzi and Hirotaka, Takano and Junichi, Murata (2013) A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization. In: Proceedings of SICE Annual Conference (SICE), 14-17 Sept. 2013 , Nagoya, Japan. pp. 1326-1331..
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Malaysia Pahang
building	UMP Institutional Repository
collection	Online Access
language	English
topic	TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering Ahmad Afif, Mohd Faudzi Hirotaka, Takano Junichi, Murata A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization
description	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.
format	Conference or Workshop Item
author	Ahmad Afif, Mohd Faudzi Hirotaka, Takano Junichi, Murata
author_facet	Ahmad Afif, Mohd Faudzi Hirotaka, Takano Junichi, Murata
author_sort	Ahmad Afif, Mohd Faudzi
title	A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization
title_short	A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization
title_full	A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization
title_fullStr	A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization
title_full_unstemmed	A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization
title_sort	study on visual abstraction for reinforcement learning problem using learning vector quantization
publishDate	2013
url	http://umpir.ump.edu.my/id/eprint/6961/ http://umpir.ump.edu.my/id/eprint/6961/1/A_study_on_Visual_Abstraction_for_Reinforcement_Learning_Problem_Using_Learning_Vector_Quantization.pdf
first_indexed	2023-09-18T22:03:08Z
last_indexed	2023-09-18T22:03:08Z
_version_	1777414531736141824

A study on Visual Abstraction for Reinforcement Learning Problem Using Learning Vector Quantization

Similar Items