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

Explanation of positional evaluation by computer programs

Research Project

Project/Area Number 25330432
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Entertainment and game informatics 1
Research InstitutionThe University of Tokyo

Principal Investigator

Kaneko Tomoyuki  東京大学, 大学院情報学環, 准教授 (00345068)

Project Period (FY) 2013-04-01 – 2016-03-31
Project Status Completed (Fiscal Year 2015)
Budget Amount *help
¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2014: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2013: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Keywordsゲームプログラミング / 探索 / 機械学習 / ゲーム情報学 / 人工知能
Outline of Final Research Achievements

The ultimate goal of this research is to present backgrounds and reasons of decisions made by computer programs, in a human-friendly manner. We focus on games such as shogi or go, because computer programs enhanced by game tree search and machine learning techniques are able to play decently as well as top-level human players do. We have developed a method for estimating relevance of possible future positions to be commented and improved its performance where the effectiveness of the method is evaluated through actual game records.

Report

(4 results)
  • 2015 Annual Research Report   Final Research Report ( PDF )
  • 2014 Research-status Report
  • 2013 Research-status Report
  • Research Products

    (21 results)

All 2016 2015 2014 2013

All Journal Article (15 results) (of which Open Access: 4 results,  Peer Reviewed: 14 results,  Acknowledgement Compliant: 2 results) Presentation (6 results) (of which Int'l Joint Research: 1 results,  Invited: 2 results)

  • [Journal Article] Monte Carlo Tree Search with Robust Exploration2016

    • Author(s)
      T. Imagawa and T. Kaneko
    • Journal Title

      Computers and Games 2016

      Volume: LNCS

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 将棋の棋譜の指し手から意図を読みとる2015

    • Author(s)
      金子 知適
    • Journal Title

      情報学環紀要

      Volume: 89 Pages: 119-122

    • Related Report
      2015 Annual Research Report
    • Open Access
  • [Journal Article] Enhancements in Monte Carlo Tree Search Algorithms for Biased Game Trees2015

    • Author(s)
      T. Imagawa and T. Kaneko
    • Journal Title

      the 2015 IEEE Conference on Computational Intelligence and Games

      Volume: LNCS Pages: 43-50

    • DOI

      10.1109/cig.2015.7317924

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Estimating Ratings of Computer Players by the Evaluation Scores and Principal Variations in Shogi2015

    • Author(s)
      S. Takeuchi and T. Kaneko
    • Journal Title

      2nd International Conference on Computational Science and Intelligence

      Volume: LNCS Pages: 85-90

    • DOI

      10.1109/acit-csi.2015.23

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Parameter-Free Tree Style Pipeline in Asynchronous Parallel Game-Tree Search2015

    • Author(s)
      S. Yokoyama, T. Kaneko, and T. Tetsuro
    • Journal Title

      The 14th International Conference on Advances in Computer and Games

      Volume: LNCS Pages: 210-222

    • DOI

      10.1007/978-3-319-27992-3_19

    • ISBN
      9783319279916, 9783319279923
    • Related Report
      2015 Annual Research Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] LinUCB Applied to Monte Carlo Tree Search2015

    • Author(s)
      Y. Mandai and T. Kaneko
    • Journal Title

      The 14th International Conference on Advances in Computer and Games

      Volume: LNCS Pages: 41-52

    • DOI

      10.1007/978-3-319-27992-3_5

    • NAID

      170000087238

    • ISBN
      9783319279916, 9783319279923
    • Related Report
      2015 Annual Research Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] Large-Scale Optimization for Evaluation Functions with Minimax Search2014

    • Author(s)
      K. Hoki and T. Kaneko
    • Journal Title

      Journal of Artificial Intelligence Research

      Volume: 49 Pages: 527-568

    • DOI

      10.1613/jair.4217

    • Related Report
      2014 Research-status Report 2013 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] 難しさが手番で異なる局面での モンテカルロ木探索の性能の改善2014

    • Author(s)
      今川 孝久,金子 知適
    • Journal Title

      情報処理学会論文誌

      Volume: 55(11) Pages: 2353-2361

    • NAID

      170000078726

    • Related Report
      2014 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] 局面の局所的な類似性を利用した モンテカルロ木探索の効率化2014

    • Author(s)
      志水 翔,金子 知適
    • Journal Title

      情報処理学会論文誌

      Volume: 55(11) Pages: 2362-2369

    • NAID

      110009550125

    • Related Report
      2014 Research-status Report
    • Peer Reviewed
  • [Journal Article] 将棋の自動解説の試み2014

    • Author(s)
      金子知適
    • Journal Title

      情報処理

      Volume: 55(8) Pages: 857-857

    • Related Report
      2014 Research-status Report
    • Peer Reviewed
  • [Journal Article] 二人ゲームプレイヤのPrior knowledgeを用いたUCTによる個性 の実現手法と評価2014

    • Author(s)
      志水翔, 金子知適
    • Journal Title

      第19回ゲームプログラミングワークショップ

      Volume: IPSJ Symposium Series 2014

    • NAID

      170000087240

    • Related Report
      2014 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] 多数の計算機を活用したゲーム木探索技術の進歩 --三浦弘行八段とGPS将棋 との対局を振り返って--2013

    • Author(s)
      金子 知適, 田中 哲朗
    • Journal Title

      情報処理

      Volume: 54(9) Pages: 914-922

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] Parallel Dovetailing and Its Application to Depth-First Proof-Number Search.2013

    • Author(s)
      Kunihito Hoki, Tomoyuki Kaneko, Akihiro Kishimoto and Takeshi Ito
    • Journal Title

      ICGA Journal

      Volume: 36(1) Pages: 22-36

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] 局面の局所的な類似性を利用したモンテカルロ木探索の効率化2013

    • Author(s)
      志水 翔, 金子 知適
    • Journal Title

      ゲームプログラミングワークショップ 2013予稿集

      Volume: 2013 Pages: 130-133

    • NAID

      110009550125

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] 難しさが手番で異なる局面でのモンテカルロ木探索の性能の改善2013

    • Author(s)
      今川 孝久, 金子 知適
    • Journal Title

      ゲームプログラミングワークショップ 2013予稿集

      Volume: 2013 Pages: 162-169

    • NAID

      170000078726

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Presentation] Machine Learning of Evaluation Functions and Playing Styles in Shogi2016

    • Author(s)
      T. Kaneko
    • Organizer
      JAIST Symposium on Game & Entertainment Technology & Its Application
    • Place of Presentation
      JAIST (石川県能美市)
    • Year and Date
      2016-02-10
    • Related Report
      2015 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] モンテカルロ木探索を統合したプレイアウト方策の最適化2015

    • Author(s)
      渡辺順哉, 美添 一樹, 金子 知適
    • Organizer
      第20回ゲームプログラミングワークショップ
    • Place of Presentation
      軽井沢学習研修所(長野県北佐久郡)
    • Year and Date
      2015-11-06
    • Related Report
      2015 Annual Research Report
  • [Presentation] 評価値を用いて展開制御したゲーム木に基づく並列探索2015

    • Author(s)
      横山秀, 金子知適
    • Organizer
      第20回ゲームプログラミングワークショップ
    • Place of Presentation
      軽井沢学習研修所(長野県北佐久郡)
    • Year and Date
      2015-11-06
    • Related Report
      2015 Annual Research Report
  • [Presentation] 囲碁における LinUCT の性能評価2015

    • Author(s)
      万代悠作, 金子知適
    • Organizer
      第20回ゲームプログラミングワークショップ
    • Place of Presentation
      軽井沢学習研修所(長野県北佐久郡)
    • Year and Date
      2015-11-06
    • Related Report
      2015 Annual Research Report
  • [Presentation] 将棋における棋風を学習するための棋譜分析の取り組み2015

    • Author(s)
      大森 翔太朗, 金子 知適
    • Organizer
      第20回ゲームプログラミングワークショップ
    • Place of Presentation
      軽井沢学習研修所(長野県北佐久郡)
    • Year and Date
      2015-11-06
    • Related Report
      2015 Annual Research Report
  • [Presentation] コンピュータ将棋はなぜ強いのか -その技術と進歩-2015

    • Author(s)
      金子知適
    • Organizer
      2015年自然科学研究教育センター・シンポジウム
    • Place of Presentation
      慶應義塾大学 (神奈川県、横浜市)
    • Year and Date
      2015-09-26
    • Related Report
      2015 Annual Research Report
    • Invited

URL: 

Published: 2014-07-25   Modified: 2019-07-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi