透過您的圖書館登入
IP:3.17.203.68
  • 會議論文
  • OpenAccess

利用平行化探勘技術萃取圍棋棋形

摘要


近年來電腦圍棋的發展大多是採用蒙地卡羅演算法。在蒙地卡羅演算法的棋局模擬中,棋形扮演相當關鍵的角色。本研究運用叢集運算的技術,從大量的棋譜中探勘出重要的棋形,並決定棋形在不同位置的權重,進而建立九路圍棋開局知識庫。

並列摘要


In recent years, the development of computer Go mostly use Monte Carlo algorithm. In the Monte Carlo simulation algorithm, patterns play an important role. In this research, we use cluster computing technology to mining crucial patterns from a large number of go game records, and to determine the weight of these patterns at different locations. Finally we build a 9x9 Go opening database by reinforce learning using the patterns.

延伸閱讀