Learning to predict life and death from Go game records
نویسندگان
چکیده
This paper presents a learning system for predicting life and death in the game of Go. Learning examples are extracted from game records. On average our system correctly predicts life and death for 88% of all blocks. Towards the end of a game the performance increases up to 99%. Clearly, such a predictor will be an important component for building a full-board evaluation function.
منابع مشابه
Learning to Score Final Positions in the Game of Go
This article investigates the application of machine-learning techniques for the task of scoring final positions in the game of Go. Neural network classifiers are trained to classify life and death from labelled 9 9 game records. The performance is compared to standard classifiers from statistical pattern recognition. A recursive framework for classification is used to improve performance itera...
متن کاملLearning on Graphs in the Game of Go
We consider the game of Go from the point of view of machine learning and as a well-deened domain for learning on graph representations. We discuss the representation of both board positions and candidate moves and introduce the common fate graph (CFG) as an adequate representation of board positions for learning. Single candidate moves are represented as feature vectors with features given by ...
متن کاملModelling Uncertainty in the Game of Go
Go is an ancient oriental game whose complexity has defeated attempts to automate it. We suggest using probability in a Bayesian sense to model the uncertainty arising from the vast complexity of the game tree. We present a simple conditional Markov random field model for predicting the pointwise territory outcome of a game. The topology of the model reflects the spatial structure of the Go boa...
متن کاملImitation Learning in The Game of Go with Joseki Options
Scaling reinforcement learning methods to large, challenging decision making tasks can potentially benefit from integrating domain specific knowledge in a principled manner. This synthesis focuses on applying two forms of domain knowledge about the game of Go to improve learning performance on what continues to be an extremely challenging task. First, learning is bootstrapped by using reinforce...
متن کاملLearning to Play the Game of Go
The problem of creating a successful artificial intelligence game playing program for the game of Go represents an important milestone in the history of computer science, and provides an interesting domain for the development of both new and existing problem-solving methods. In particular, the problem of Go can be used as a benchmark for machine learning techniques. Most commercial Go playing p...
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:
- Inf. Sci.
دوره 175 شماره
صفحات -
تاریخ انتشار 2005