政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/53397
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文笔数/总笔数 : 109953/140892 (78%)
造访人次 : 46223031      在线人数 : 635
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧：
  • 您可在西文检索词汇前后加上"双引号"，以获取较精准的检索结果
  • 若欲以作者姓名搜寻，建议至进阶搜寻限定作者字段，可获得较完整数据
    •  进阶搜寻


    请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/53397


    题名: 貝氏評分系統(II)
    其它题名: Bayesian Rating System
    作者: 翁久幸
    贡献者: 國立政治大學統計學系
    行政院國家科學委員會
    关键词: 數學;貝氏評分系統
    日期: 2009
    上传时间: 2012-08-30 09:59:10 (UTC+8)
    摘要: 許多球類,棋藝,遊戲比賽,都有對各個參賽者實力作排名,目前有線上(online)與非線 上(offline) 排名方法. 線上排名(online rating)方法與非線上排名(offline rating)方法的主要差別在於前者不用儲存過去大量比賽結果. 由於許多比賽(特別 是線上遊戲)不僅參賽者多,而且比賽場次也多,每天可能就有上百萬參與者和場次. 線上排名方法不需要儲存過去大量比賽結果的特性,使得它廣受使用. 目前最有名的排名方法是Elo. 它被相當成功地用在許多兩人比賽之球類,棋藝等. 之後, Glickman 提出Glicko System. 它與Elo 的主要差別在於前者在"實力’這個 參數上引進變異(variability)的觀念. Glicko 也被成功地用在許多兩人比賽 隨著線上遊戲時代的到來,許多多人多隊比賽的遊戲越來越普遍. 如何評定各個參賽 者之實力也成為需要研究的問題.對此問題,最近Microsoft Research 提出一個評分 系統TrueSkill. 本計畫擬討論TrueSkill 之優缺點,然後提出一個簡易有效之評分 系統. 並且我們要以Halo 2 dataset (the beta testing of the Xbox)來測試我們 評分系統之表現.
    There are some rating systems for sports, chess, and games. Some systems are online and some are offline. The main difference between online and offline is that the former does not need to store all the past data. Since many games (especially online games) involve a huge number of players and everyday there could be millions of games played, the online rating system is more suited to be used in such situation. Many have proposed online algorithms for paired comparison experiments. These For ranking of many sports, possibly the most prominent ranking system in use today is ELO, originally invented by Arpad Elo, as an improved chess rating system and now it has been used successfully by a variety of leagues organized around two-player games. Another famous updating algorithm is the Glicko system, developed by Mark E. Glickman, chairman of the US Chess Federation (USCF) ratings committee. The main difference between Elo and Glicko is that the later introduced “variability”into the skill parameter. Though the ELO and Glicko ranking system have been successfully, they are designed for two-player games. In video games many of these leagues have game modes with more than two players (and/or more than two teams) per match. To support such games, recently Microsoft Research developed the TrueSkill ranking system. In this project, we propose to use an approximate Bayesian method together with a generalization of the Bradley-Terry model to obtain simple update formulas in cases where there may be multiple teams and/or multiple players.
    關聯: 基礎研究
    學術補助
    研究期間:9808~ 9907
    研究經費:522仟元
    数据类型: report
    显示于类别:[統計學系] 國科會研究計畫

    文件中的档案:

    档案 大小格式浏览次数
    98211M002.pdf185KbAdobe PDF2781检视/开启


    在政大典藏中所有的数据项都受到原著作权保护.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈