Monte Carlo Go Has a Way to Go
نویسندگان
چکیده
Monte Carlo Go is a promising method to improve the performance of computer Go programs. This approach determines the next move to play based on many Monte Carlo samples. This paper examines the relative advantages of additional samples and enhancements for Monte Carlo Go. By parallelizing Monte Carlo Go, we could increase sample sizes by two orders of magnitude. Experimental results obtained in 9 × 9 Go show strong evidence that there are trade-offs among these advantages and performance, indicating a way for Monte Carlo Go to go.
منابع مشابه
Combining Tactical Search and Monte-Carlo in the Game of Go
We present a way to integrate search and Monte-Carlo methods in the game of Go. Our program uses search to find the status of tactical goals, builds groups, selects interesting goals, and computes statistics on the realization of tactical goals during the random games. The mean score of the random games where a selected tactical goal has been reached and the mean score of the random games where...
متن کاملPh D in Computer Games and Artificial Intelligence
The field of study of the PhD position offered is Computer Games (CG) and Artificial Intelligence (AI) in general. More precisely the games studied are zero-sum two-player complete information games with a high complexity such as Go, Amazons or Shogi. In addition to Tree Search (TS) and knowledge-based techniques, the technique newly used in the computer Go community is Monte-Carlo (MC) [5]. Th...
متن کاملExploration exploitation in Go: UCT for Monte-Carlo Go
Algorithm UCB1 for multi-armed bandit problem has already been extended to Algorithm UCT which works for minimax tree search. We have developed a Monte-Carlo program, MoGo, which is the first computer Go program using UCT. We explain our modifications of UCT for Go application, among which efficient memory management, parametrization, ordering of non-visited nodes and parallelization. MoGo is n...
متن کاملModification of UCT with Patterns in Monte-Carlo Go
Algorithm UCB1 for multi-armed bandit problem has already been extended to Algorithm UCT (Upper bound Confidence for Tree) which works for minimax tree search. We have developed a Monte-Carlo Go program, MoGo, which is the first computer Go program using UCT. We explain our modification of UCT for Go application and also the intelligent random simulation with patterns which has improved signifi...
متن کاملMonte-Carlo tree search and rapid action value estimation in computer Go
A new paradigm for search, based on Monte-Carlo simulation, has revolutionised the performance of computer Go programs. In this article we describe two extensions to the Monte-Carlo tree search algorithm, which significantly improve the effectiveness of the basic algorithm. When we applied these two extensions to the Go program MoGo, it became the first program to achieve dan (master) level at ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006