• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Swarm Reinforcement Learning Methods Based on PSO for Complicated Learning Problems

Research Project

Project/Area Number 22500131
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionKyoto Institute of Technology

Principal Investigator

IIMA Hitoshi  京都工芸繊維大学, 工芸科学研究科, 准教授 (70273547)

Co-Investigator(Kenkyū-buntansha) KUROE Yasuaki  京都工芸繊維大学, 工芸科学研究科, 教授 (10153397)
Project Period (FY) 2010 – 2012
Project Status Completed (Fiscal Year 2012)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2012: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2011: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2010: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Keywords強化学習 / PSO / 群知能 / Particile Swarm Optimization / Particle Swarm Optimization
Research Abstract

We proposed swarm reinforcement learning methods based on particle swarm optimization (PSO) for acquiring optimal policies rapidly, and applied the proposed methods to some complicated reinforcement learning problems such as ones with continuous state-action space. In the proposed method, multiple sets of an agent and an environment, which are called learning worlds, are prepared, and agents in each learning world learn not only by individually using a usual reinforcement learning method but also through exchanging information among the learning worlds by using the update equations of PSO.

Report

(4 results)
  • 2012 Annual Research Report   Final Research Report ( PDF )
  • 2011 Annual Research Report
  • 2010 Annual Research Report
  • Research Products

    (29 results)

All 2013 2012 2011 2010

All Journal Article (11 results) (of which Peer Reviewed: 11 results) Presentation (18 results)

  • [Journal Article] Swarm Reinforcement Learning Method for Multi-agent Tasks2013

    • Author(s)
      山分翔太
    • Journal Title

      Transactions of the Society of Instrument and Control Engineers

      Volume: 49 Issue: 3 Pages: 370-377

    • DOI

      10.9746/sicetr.49.370

    • NAID

      10031160127

    • ISSN
      0453-4654, 1883-8189
    • Related Report
      2012 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Swarm Reinforcement Learning Methods for Problems with Continuous State-action Space2012

    • Author(s)
      飯間 等、黒江康明
    • Journal Title

      Transactions of the Society of Instrument and Control Engineers

      Volume: 48 Issue: 11 Pages: 790-798

    • DOI

      10.9746/sicetr.48.790

    • NAID

      130004549594

    • ISSN
      0453-4654, 1883-8189
    • Related Report
      2012 Annual Research Report 2012 Final Research Report
    • Peer Reviewed
  • [Journal Article] Multi-Objective Reinforcement Learning Method for Acquiring All Pareto Optimal Policies Simultaneously2012

    • Author(s)
      Yusuke Mukai、Yasuaki Kuroe、Hitoshi Iima
    • Journal Title

      Proceedings of 2012 IEEE International Conference on Systems, Man and Cybernetics

      Pages: 1917-1923

    • DOI

      10.1109/icsmc.2012.6378018

    • Related Report
      2012 Final Research Report
    • Peer Reviewed
  • [Journal Article] Multi-Objective Reinforcement Learning Method for Acquiring All Pareto Optimal Policies Simultaneously2012

    • Author(s)
      Yusuke Mukai
    • Journal Title

      Proceedings of 2012 IEEE International Conference on Systems, Man and Cybernetics

      Volume: 1 Pages: 1917-1923

    • Related Report
      2012 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Swarm Reinforcement Learning Methods for Problems with Continuous State-Action Space2011

    • Author(s)
      Hitoshi Iima 、Yasuaki Kuroe 、Kazuo Emoto
    • Journal Title

      Proceedings of 2011 IEEE International Conference on Systems, Man and Cybernetics

      Pages: 2173-2180

    • DOI

      10.1109/icsmc.2011.6083999

    • NAID

      10031128047

    • Related Report
      2012 Final Research Report
    • Peer Reviewed
  • [Journal Article] Swarm Reinforcement Learning Method for Multi-Agent Tasks-Solution of Dilemma Problems-2011

    • Author(s)
      Shota Yamawake, Hitoshi Iima, Yasuaki Kuroe
    • Journal Title

      Proceedings of SICE Annual Conference 2011

      Volume: (CD-ROM)

    • NAID

      10031160127

    • Related Report
      2011 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Swarm Reinforcement Learning Methods for Problems with Continuous State-Action Space2011

    • Author(s)
      Hitoshi Iima, Yasuaki Kuroe, Kazuo Emoto
    • Journal Title

      Proceedings of IEEE International Conference on Systems, Man and Cybernetics

      Volume: 1 Pages: 2173-2180

    • NAID

      10031128047

    • Related Report
      2011 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Swarm Reinforcement Learning Method Based on an Actor-Critic2010

    • Author(s)
      Hitoshi Iima 、Yasuaki Kuroe
    • Journal Title

      Proceedings of Eighth International Conference on Simulated Evolution and Learning

      Pages: 279-288

    • DOI

      10.1007/978-3-642-17298-4_29

    • ISBN
      9783642172977, 9783642172984
    • Related Report
      2012 Final Research Report
    • Peer Reviewed
  • [Journal Article] Particle Swarm Optimizationによるリカレントスパイキングニューラルネットワークの学習法2010

    • Author(s)
      山本昌弘、黒江康明、飯間等
    • Journal Title

      計測自動制御学会論文集

      Volume: 46 Pages: 685-691

    • NAID

      10027445731

    • Related Report
      2010 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Swarm Reinforcement Learning Method Based on Ant Colony Optimization2010

    • Author(s)
      Hitoshi Iima, Yasuaki Kuroe, Shoko Matsuda
    • Journal Title

      Proceedings of IEEE International Conference on Systems, Man and Cybernetics

      Volume: 1 Pages: 1726-1733

    • Related Report
      2010 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Swarm Reinforcement Learning Method Based on an Actor-Critic Method2010

    • Author(s)
      Hitoshi Iima, Yasuaki Kuroe
    • Journal Title

      Proceedings of Eighth International Conference on Simulated Evolution and Learning

      Volume: 1

    • Related Report
      2010 Annual Research Report
    • Peer Reviewed
  • [Presentation] Particle Swarm Optimization に基づくタイルコーディングを用いた強化学習法2013

    • Author(s)
      伊藤 洋
    • Organizer
      計測自動制御学会第40回知能システムシンポジウ
    • Place of Presentation
      京都工芸繊維大学
    • Year and Date
      2013-03-14
    • Related Report
      2012 Final Research Report
  • [Presentation] Particle Swarm Optimizationに基づくタイルコーディングを用いた強化学習法2013

    • Author(s)
      伊藤 洋
    • Organizer
      第40回知能システムシンポジウム
    • Place of Presentation
      京都工芸繊維大学
    • Related Report
      2012 Annual Research Report
  • [Presentation] 優越関係を用いたすべてのパレート最適方策を同時に獲得する多目的強化学習法2013

    • Author(s)
      向井悠祐
    • Organizer
      第40回知能システムシンポジウム
    • Place of Presentation
      京都工芸繊維大学
    • Related Report
      2012 Annual Research Report
  • [Presentation] あるクラスのジレンマ問題に対するマルチエージェント強化学習法2013

    • Author(s)
      高尾 晃
    • Organizer
      第40回知能システムシンポジウム
    • Place of Presentation
      京都工芸繊維大学
    • Related Report
      2012 Annual Research Report
  • [Presentation] フォーメーション形成問題に対するParticle Swarm Optimization に基づく群強化学習法2012

    • Author(s)
      飯間 等
    • Organizer
      第57回システム制御情報学会研究発表講演会
    • Place of Presentation
      兵庫県民会館
    • Year and Date
      2012-05-17
    • Related Report
      2012 Final Research Report
  • [Presentation] すべてのパレート最適方策を同時に獲得する多目的強化学習法2012

    • Author(s)
      向井悠祐
    • Organizer
      第39回知能システムシンポジウム
    • Place of Presentation
      千葉大学
    • Year and Date
      2012-03-16
    • Related Report
      2011 Annual Research Report
  • [Presentation] ジレンマ問題に対するマルチエージェントタスク強化学習法2012

    • Author(s)
      山分翔太
    • Organizer
      第39回知能システムシンポジウム
    • Place of Presentation
      千葉大学
    • Year and Date
      2012-03-15
    • Related Report
      2011 Annual Research Report
  • [Presentation] 複数ロボットのフォーメーション形成問題に対する群強化学習法2012

    • Author(s)
      飯間 等
    • Organizer
      第22回インテリジェント・システム・シンポジウム
    • Place of Presentation
      てだこホール
    • Related Report
      2012 Annual Research Report
  • [Presentation] 複数ロボットのフォーメーション形成問題に対する群強化学習法とその評価2012

    • Author(s)
      飯間 等
    • Organizer
      計測自動制御学会システム・情報部門学術講演会2012
    • Place of Presentation
      ウィルあいち
    • Related Report
      2012 Annual Research Report
  • [Presentation] 高次元連続状態行動空間の問題に対する群強化学習法2011

    • Author(s)
      飯間 等
    • Organizer
      計測自動制御学会システム・情報部門学術講演会2011
    • Place of Presentation
      東京都国立オリンピック記念青少年総合センター
    • Year and Date
      2011-11-21
    • Related Report
      2012 Final Research Report
  • [Presentation] 高次元連続状態行動空間の問題に対する群強化学習法2011

    • Author(s)
      飯間, 等
    • Organizer
      システム・情報部門学術講演会2011
    • Place of Presentation
      東京都国立オリンピック記念青少年総合センター
    • Year and Date
      2011-11-21
    • Related Report
      2011 Annual Research Report
  • [Presentation] マルチエージェントタスクの群強化学習法による解法-ジレンマ問題に向けて-2011

    • Author(s)
      山分翔太
    • Organizer
      第21回インテリジェント・システム・シンポジウム
    • Place of Presentation
      神戸大学
    • Year and Date
      2011-09-02
    • Related Report
      2011 Annual Research Report
  • [Presentation] 寿命を設定した自己最良値を用いたParticle Swarm Optimizationに基づく群強化学習法2011

    • Author(s)
      飯間, 等
    • Organizer
      第55回システム制御情報学会研究発表講演会
    • Place of Presentation
      大阪大学
    • Year and Date
      2011-05-19
    • Related Report
      2011 Annual Research Report
  • [Presentation] 様々な発火パターンを実現するParticle Swarm Optimizationによるスパイキングニューラルネットワークの学習法2011

    • Author(s)
      山本昌弘
    • Organizer
      第38回知能システムシンポジウム
    • Place of Presentation
      神戸
    • Year and Date
      2011-03-17
    • Related Report
      2010 Annual Research Report
  • [Presentation] 寿命を設定した自己最良値を用いたParticle Swarm Optimization に基づく群強化学習法2010

    • Author(s)
      飯間 等
    • Organizer
      計測自動制御学会システム・情報部門学術講演会2010 講演論文集
    • Place of Presentation
      キャンパスプラザ京都
    • Year and Date
      2010-11-25
    • Related Report
      2012 Final Research Report
  • [Presentation] 繰り返しN人囚人のジレンマ問題の群強化学習による解法2010

    • Author(s)
      山分翔太
    • Organizer
      第20回インテリジェントシステム・シンポジウム
    • Place of Presentation
      東京
    • Year and Date
      2010-09-25
    • Related Report
      2010 Annual Research Report
  • [Presentation] 寿命のある自己最良値を用いたParticle Swarm Optimization に基づく群強化学習法2010

    • Author(s)
      飯間 等
    • Organizer
      第54回システム制御情報学会研究発表講演会
    • Place of Presentation
      京都リサーチパーク
    • Year and Date
      2010-05-19
    • Related Report
      2012 Final Research Report
  • [Presentation] 寿命のある自己最良値を用いたParticle Swarm Optimizationに基づく群強化学習法2010

    • Author(s)
      飯間等
    • Organizer
      第54回システム制御情報学会研究発表講演会
    • Place of Presentation
      京都
    • Year and Date
      2010-05-19
    • Related Report
      2010 Annual Research Report

URL: 

Published: 2010-08-23   Modified: 2019-07-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi