Task-oriented reinforcement learning for continuing task in dynamic environment

Md Abdus Samad Kamal, Junichi Murata, Kotaro Hirasawa

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper presents task-oriented reinforcement learning, a modified approach of reinforcement-learning to simplify continuing dynamic problems in a more realistic and human-like way of thinking from the viewpoint of the tasks. In this learning method an agent takes as input the 'state of task' instead of 'state of environment' and chooses appropriate action to achieve the goal of the corresponding task. The proposed system learns from the viewpoint of tasks that enables the system to find and follow a precise policy in a continuing-dynamic environment and offers simple implementation for a multiple agents system.

Original languageEnglish
Pages (from-to)7-12
Number of pages6
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume9
Issue number1
Publication statusPublished - Mar 1 2004

Fingerprint

Reinforcement learning

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Task-oriented reinforcement learning for continuing task in dynamic environment. / Kamal, Md Abdus Samad; Murata, Junichi; Hirasawa, Kotaro.

In: Research Reports on Information Science and Electrical Engineering of Kyushu University, Vol. 9, No. 1, 01.03.2004, p. 7-12.

Research output: Contribution to journalArticle

@article{e86625891b0b4cba821b1113cf1f7089,
title = "Task-oriented reinforcement learning for continuing task in dynamic environment",
abstract = "This paper presents task-oriented reinforcement learning, a modified approach of reinforcement-learning to simplify continuing dynamic problems in a more realistic and human-like way of thinking from the viewpoint of the tasks. In this learning method an agent takes as input the 'state of task' instead of 'state of environment' and chooses appropriate action to achieve the goal of the corresponding task. The proposed system learns from the viewpoint of tasks that enables the system to find and follow a precise policy in a continuing-dynamic environment and offers simple implementation for a multiple agents system.",
author = "Kamal, {Md Abdus Samad} and Junichi Murata and Kotaro Hirasawa",
year = "2004",
month = "3",
day = "1",
language = "English",
volume = "9",
pages = "7--12",
journal = "Research Reports on Information Science and Electrical Engineering of Kyushu University",
issn = "1342-3819",
publisher = "Kyushu University, Faculty of Science",
number = "1",

}

TY - JOUR

T1 - Task-oriented reinforcement learning for continuing task in dynamic environment

AU - Kamal, Md Abdus Samad

AU - Murata, Junichi

AU - Hirasawa, Kotaro

PY - 2004/3/1

Y1 - 2004/3/1

N2 - This paper presents task-oriented reinforcement learning, a modified approach of reinforcement-learning to simplify continuing dynamic problems in a more realistic and human-like way of thinking from the viewpoint of the tasks. In this learning method an agent takes as input the 'state of task' instead of 'state of environment' and chooses appropriate action to achieve the goal of the corresponding task. The proposed system learns from the viewpoint of tasks that enables the system to find and follow a precise policy in a continuing-dynamic environment and offers simple implementation for a multiple agents system.

AB - This paper presents task-oriented reinforcement learning, a modified approach of reinforcement-learning to simplify continuing dynamic problems in a more realistic and human-like way of thinking from the viewpoint of the tasks. In this learning method an agent takes as input the 'state of task' instead of 'state of environment' and chooses appropriate action to achieve the goal of the corresponding task. The proposed system learns from the viewpoint of tasks that enables the system to find and follow a precise policy in a continuing-dynamic environment and offers simple implementation for a multiple agents system.

UR - http://www.scopus.com/inward/record.url?scp=3543115032&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3543115032&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:3543115032

VL - 9

SP - 7

EP - 12

JO - Research Reports on Information Science and Electrical Engineering of Kyushu University

JF - Research Reports on Information Science and Electrical Engineering of Kyushu University

SN - 1342-3819

IS - 1

ER -