R-learning with multiple state-action value tables

Koichiro Ishikawa, Akito Sakurai, Tsutomu Fujinami, Susumu Kunifuji

Research output: Contribution to journalArticle

Abstract

We propose a method to improve the performance of R-learning, a reinforcement learning algorithm, by using multiple state-action value tables. Unlike Q- or Sarsa learning, R-learning learns a policy to maximize undiscounted rewards. Multiple state-action value tables cause substantial explorations as needed and make R-learnings to work well. Efficiency of the proposed method is verified through experiments in simulation environment.

Original languageEnglish
Pages (from-to)72-82
Number of pages11
JournalIEEJ Transactions on Electronics, Information and Systems
Volume126
Issue number1
DOIs
Publication statusPublished - 2006

Fingerprint

Reinforcement learning
Learning algorithms
Experiments

Keywords

  • Autonomous mobile robot
  • R-learning
  • Reinforcement learning

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

R-learning with multiple state-action value tables. / Ishikawa, Koichiro; Sakurai, Akito; Fujinami, Tsutomu; Kunifuji, Susumu.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 126, No. 1, 2006, p. 72-82.

Research output: Contribution to journalArticle

Ishikawa, Koichiro ; Sakurai, Akito ; Fujinami, Tsutomu ; Kunifuji, Susumu. / R-learning with multiple state-action value tables. In: IEEJ Transactions on Electronics, Information and Systems. 2006 ; Vol. 126, No. 1. pp. 72-82.
@article{cadf0edb86324f8d9c261f43f2d835fb,
title = "R-learning with multiple state-action value tables",
abstract = "We propose a method to improve the performance of R-learning, a reinforcement learning algorithm, by using multiple state-action value tables. Unlike Q- or Sarsa learning, R-learning learns a policy to maximize undiscounted rewards. Multiple state-action value tables cause substantial explorations as needed and make R-learnings to work well. Efficiency of the proposed method is verified through experiments in simulation environment.",
keywords = "Autonomous mobile robot, R-learning, Reinforcement learning",
author = "Koichiro Ishikawa and Akito Sakurai and Tsutomu Fujinami and Susumu Kunifuji",
year = "2006",
doi = "10.1541/ieejeiss.126.72",
language = "English",
volume = "126",
pages = "72--82",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "1",

}

TY - JOUR

T1 - R-learning with multiple state-action value tables

AU - Ishikawa, Koichiro

AU - Sakurai, Akito

AU - Fujinami, Tsutomu

AU - Kunifuji, Susumu

PY - 2006

Y1 - 2006

N2 - We propose a method to improve the performance of R-learning, a reinforcement learning algorithm, by using multiple state-action value tables. Unlike Q- or Sarsa learning, R-learning learns a policy to maximize undiscounted rewards. Multiple state-action value tables cause substantial explorations as needed and make R-learnings to work well. Efficiency of the proposed method is verified through experiments in simulation environment.

AB - We propose a method to improve the performance of R-learning, a reinforcement learning algorithm, by using multiple state-action value tables. Unlike Q- or Sarsa learning, R-learning learns a policy to maximize undiscounted rewards. Multiple state-action value tables cause substantial explorations as needed and make R-learnings to work well. Efficiency of the proposed method is verified through experiments in simulation environment.

KW - Autonomous mobile robot

KW - R-learning

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=33749571691&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749571691&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.126.72

DO - 10.1541/ieejeiss.126.72

M3 - Article

AN - SCOPUS:33749571691

VL - 126

SP - 72

EP - 82

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 1

ER -