Cover Image

A Study on Abstract Policy for Acceleration of Reinforcement Learning

Reinforcement learning (RL) is well known as one of the methods that can be applied to unknown problems. However, because optimization at every state requires trial-and-error, the learning time becomes large when environment has many states. If there exist solutions to similar problems and they are...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmad Afif, Mohd Faudzi, Hirotaka, Takano, Junichi, Murata
Format: Conference or Workshop Item
Language:English
Published: 2014
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
Online Access:http://umpir.ump.edu.my/id/eprint/7452/1/A_Study_on_Abstract_Policy_for_Acceleration_of_Reinforcement_Learning.pdf
http://umpir.ump.edu.my/id/eprint/7452/
http://dx.doi.org/10.1109/SICE.2014.6935300
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ump.umpir.7452
record_format eprints
spelling my.ump.umpir.74522016-04-19T07:31:26Z http://umpir.ump.edu.my/id/eprint/7452/ A Study on Abstract Policy for Acceleration of Reinforcement Learning Ahmad Afif, Mohd Faudzi Hirotaka, Takano Junichi, Murata TK Electrical engineering. Electronics Nuclear engineering Reinforcement learning (RL) is well known as one of the methods that can be applied to unknown problems. However, because optimization at every state requires trial-and-error, the learning time becomes large when environment has many states. If there exist solutions to similar problems and they are used during the exploration, some of trial-anderror can be spared and the learning can take a shorter time. In this paper, the authors propose to reuse an abstract policy, a representative of a solution constructed by learning vector quantization (LVQ) algorithm, to improve initial performance of an RL learner in a similar but different problem. Furthermore, it is investigated whether or not the policy can adapt to a new environment while preserving its performance in the old environments. Simulations show good result in terms of the learning acceleration and the adaptation of abstract policy. 2014 Conference or Workshop Item PeerReviewed application/pdf en http://umpir.ump.edu.my/id/eprint/7452/1/A_Study_on_Abstract_Policy_for_Acceleration_of_Reinforcement_Learning.pdf Ahmad Afif, Mohd Faudzi and Hirotaka, Takano and Junichi, Murata (2014) A Study on Abstract Policy for Acceleration of Reinforcement Learning. In: Proceedings of the SICE Annual Conference (SICE), 9-12 Sept. 2014 , Sapporo, Japan. pp. 1793-1798.. http://dx.doi.org/10.1109/SICE.2014.6935300
institution Universiti Malaysia Pahang
building UMP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Pahang
content_source UMP Institutional Repository
url_provider http://umpir.ump.edu.my/
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 Abstract Policy for Acceleration of Reinforcement Learning
description Reinforcement learning (RL) is well known as one of the methods that can be applied to unknown problems. However, because optimization at every state requires trial-and-error, the learning time becomes large when environment has many states. If there exist solutions to similar problems and they are used during the exploration, some of trial-anderror can be spared and the learning can take a shorter time. In this paper, the authors propose to reuse an abstract policy, a representative of a solution constructed by learning vector quantization (LVQ) algorithm, to improve initial performance of an RL learner in a similar but different problem. Furthermore, it is investigated whether or not the policy can adapt to a new environment while preserving its performance in the old environments. Simulations show good result in terms of the learning acceleration and the adaptation of abstract policy.
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 Abstract Policy for Acceleration of Reinforcement Learning
title_short A Study on Abstract Policy for Acceleration of Reinforcement Learning
title_full A Study on Abstract Policy for Acceleration of Reinforcement Learning
title_fullStr A Study on Abstract Policy for Acceleration of Reinforcement Learning
title_full_unstemmed A Study on Abstract Policy for Acceleration of Reinforcement Learning
title_sort study on abstract policy for acceleration of reinforcement learning
publishDate 2014
url http://umpir.ump.edu.my/id/eprint/7452/1/A_Study_on_Abstract_Policy_for_Acceleration_of_Reinforcement_Learning.pdf
http://umpir.ump.edu.my/id/eprint/7452/
http://dx.doi.org/10.1109/SICE.2014.6935300
_version_ 1643665621732294656
score 13.211869

Similar Items