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

How to Coach Human Players using Computer Go Program

Research Project

Project/Area Number 17K00506
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Entertainment and game informatics 1
Research InstitutionJapan Advanced Institute of Science and Technology

Principal Investigator

Ikeda Kokolo  北陸先端科学技術大学院大学, 先端科学技術研究科, 准教授 (80362416)

Project Period (FY) 2017-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2017: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Keywords教えるAI / 楽しませるAI / 囲碁 / 深層学習 / コンテンツ生成 / PCG / 指導 / パズル / 自動コンテンツ生成 / 指導碁 / 接待碁 / テトリス / ガイスター / RPG / 上海 / リズムゲーム / 楽しませる / ゲーム / 教師あり学習 / 深層強化学習 / 教える / 人間らしさ / 問題生成 / PCG / 弱点発見 / ぷよぷよ / ゲームプログラミング
Outline of Final Research Achievements

Recently, artificial intelligence methods have been greatly improved and affected human life. In the area of game informatics, super-human level computer players have been developed for many games including Go or Japanese Chess. So, not only just strong computer players, but also entertaining computer players or educating computer programs are attracting attentions.
In this research, entertaining computer program using very strong deep learning computer Go program has been tried. For the purpose, computer players should select non-optimal moves intentionally, but such intentional bad moves should not be detected by human players. In addition, not only single play style, but also various play styles for example "center-oriented" or "edge/corner-oriented" should be served. Many ideas were proposed and their values were confirmed through experiments using subjects. Further, procedural contents generation for education was tried using many games, such as VS-tetris, geister, or rhythm games.

Academic Significance and Societal Importance of the Research Achievements

単に強いゲームプログラムを作る場合,それは数学や情報学の中の閉じられた世界である.一方で,楽しませる・教えるゲームプログラムを作ろうと考えると,それは「人間らしさ」「人間はどんなときに楽しいのか」「人間はどう学習するのか」など,人間を理解しなければならない.その意味で本研究は情報学を教育学や心理学の方面に橋掛けする大きな基盤となっていると考える.
また,単に強いだけでなく,楽しませる・教えることを重視することで,人間があるゲームを遊んだときの満足度や,その意欲継続を向上させることに貢献している.物質的豊かさの次に精神的豊かさをもたらすものとして,社会的意義も大きいと考える.

Report

(4 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (15 results)

All 2020 2019 2018 2017

All Presentation (15 results) (of which Int'l Joint Research: 5 results,  Invited: 1 results)

  • [Presentation] 上海ゲームにおける面白いインスタンス生成2020

    • Author(s)
      森長剛志, 池田心
    • Organizer
      情報処理学会第43回ゲーム情報学研究発表会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Procedural Content Generation of Rhythm Games Using Deep Learning Methods2019

    • Author(s)
      Yubin Liang, Wanxiang Li and Kokolo Ikeda
    • Organizer
      International Conference on Entertainment Computing (ICEC) & Joint Conference on Serious Games (JCSG)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Position Control and Production of Various Strategies for Deep Learning Go Programs2019

    • Author(s)
      Tianwen Fan, Yuan Shi, Wanxiang Li and Kokolo Ikeda
    • Organizer
      International Conference on Technologies and Applications of Artificial Intelligence (TAAI 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Enhancing Human Players’ T-Spin Technique in Tetris with Procedural Problem Generation2019

    • Author(s)
      Taishi Oikawa, Chu-Hsuan Hsueh and Kokolo Ikeda
    • Organizer
      16th Advances in Computer Games Conference
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Generating Stages in Turn-Based RPG using Reinforcement Learning2019

    • Author(s)
      SangGyu Nam, Kokolo Ikeda
    • Organizer
      IEEE Conference on Games (CoG2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 難しい詰めガイスター問題の生成法2019

    • Author(s)
      石井岳史, 川上直人, 橋本剛, 池田心
    • Organizer
      第24回ゲームプログラミングワークショップ(GPW-19)
    • Related Report
      2019 Annual Research Report
  • [Presentation] 楽しませる囲碁プログラム~強すぎるAIにどう接待させるか2019

    • Author(s)
      池田心
    • Organizer
      JAPAN GO CONGRESS 2019 in KANAZAWA
    • Related Report
      2019 Annual Research Report
    • Invited
  • [Presentation] 連鎖構成力向上のための多様で面白いなぞぷよ提供法の提案2019

    • Author(s)
      牧田 光平,池田 心
    • Organizer
      情報処理学会 第41回ゲーム情報学(GI)研究発表会
    • Related Report
      2018 Research-status Report
  • [Presentation] 不完全情報ゲーム『ガイスター』における2種の詰め問題の提案と考察2019

    • Author(s)
      石井 岳史,川上 直人,橋本 剛,池田 心
    • Organizer
      情報処理学会 第41回ゲーム情報学(GI)研究発表会
    • Related Report
      2018 Research-status Report
  • [Presentation] 深層学習囲碁プログラムを用いた場合の手加減に関する研究2019

    • Author(s)
      Shi Yuan,Fan Tianwen,Li Wanxiang,池田 心
    • Organizer
      情報処理学会 第41回ゲーム情報学(GI)研究発表会
    • Related Report
      2018 Research-status Report
  • [Presentation] 強化学習を用いたターン制 RPG のステーシ自動生成2018

    • Author(s)
      ナムサンギュ,池田心
    • Organizer
      第23回ゲームプログラミングワークショップ
    • Related Report
      2018 Research-status Report
  • [Presentation] テトリスにおけるT-spin構成力向上のための問題作成2018

    • Author(s)
      及川 大志 ,池田心
    • Organizer
      第23回ゲームプログラミングワークショップ
    • Related Report
      2018 Research-status Report
  • [Presentation] リズムゲームの上達を支援するコンテンツ自動生成法2018

    • Author(s)
      Liang Yubin,池田心
    • Organizer
      情報処理学会 第39回ゲーム情報学(GI)研究発表会
    • Related Report
      2017 Research-status Report
  • [Presentation] 連鎖構成力向上のためのぷよぷよの問題作成2018

    • Author(s)
      高橋竜太郎,池田心
    • Organizer
      情報処理学会 第39回ゲーム情報学(GI)研究発表会
    • Related Report
      2017 Research-status Report
  • [Presentation] Survey of How Human Players Divert In-game Actions for Other Purposes: Towards Human-like Computer Players2017

    • Author(s)
      Sila Temsiririrkkul, Naoyuki Sato, Kenta Nakagawa, Kokolo Ikeda
    • Organizer
      International Conference on Entertainment Computing
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2017-04-28   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi