Computer Go: Knowledge, Search, and Move Decision
نویسنده
چکیده
This paper intends to provide an analytical overview of the research performed in the domain of computer Go. Domain knowledge that is essential to Go-playing programs is identified. Various computation and search techniques that can be used effectively to obtain helpful domain knowledge are presented. Four different move-decision paradigms applied by today’s leading Go programs are discussed. Conclusions are drawn and two proposals of improvements to current move-decision paradigms are presented.
منابع مشابه
The Move-Decision Strategy of Indigo
This paper describes the move decision strategy of Indigo. By using the example of Indigo, the paper shows that the move decision process of a Go program can be very different from the processes used in other games with lower complexity than the complexity of Go, even if the basic modules are conventional (move generator, evaluation function and tree search). Indigo uses them in a specific way,...
متن کاملSolving Nine Men's Morris
In recent years, a number of games have been solved using computers. These include Qubic [Patashnik 80], Connect-4 [Allen 89], [Allis 88] and Go-Moku [Allis 93]. All these games were solved using knowledge-based methods. These methods are successful because all these games have a low “decision complexity” [Allis 90], i.e., the right move is often easy to find. Not all games profit to the same e...
متن کاملPattern Knowledge for Proof-Number Search in Computer Go
Over the years, proof-number search has successfully been applied to many game domains. This article proposes two new pattern-based heuristics for move ordering in proof-number search. One heuristic applies patterns directly, the other heuristic uses patterns to control Monte-Carlo sampling. The test domain is the Life-and-Death problem in the game of Go. Experimentally, we found some advantage...
متن کاملLearning to Forecast by Explaining the Consequences of Actions
I explain a method to learn to achieve goals in games. In very complex games, such as the game of Go, a search intensive approach is intractable. A knowledge intensive approach is best suited. I represent knowledge using the combinatorial game theory and first order logic. I give a method to learn to predict the consequences of some moves. Each rule is learned using a single example, by explain...
متن کاملMove Prediction using Deep Convolutional Neural Networks in Hex
Using deep convolutional neural networks for move prediction has led to massive progress in Computer Go. Like Go, Hex has a large branching factor that limits the success of shallow and selective search. We show that deep convolutional neural networks can be used to produce reliable move evaluation in the game of Hex. We begin by collecting self-play games of MoHex 2.0. We then train the neural...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- ICGA Journal
دوره 24 شماره
صفحات -
تاریخ انتشار 2001