A generalised quiescence search algorithm
Artificial Intelligence - Special issue on computer chess
Expected-Outcome: A General Model of Static Evaluation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Static analysis of life and death in the game of Go
Information Sciences—Informatics and Computer Science: An International Journal
Computer Go: an AI oriented survey
Artificial Intelligence
Finite-time Analysis of the Multiarmed Bandit Problem
Machine Learning
Heuristic analysis of large trees as generated in the game of 'go'
Heuristic analysis of large trees as generated in the game of 'go'
The Journal of Machine Learning Research
Information Sciences: an International Journal
Exploiting graph properties of game trees
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Bandit based monte-carlo planning
ECML'06 Proceedings of the 17th European conference on Machine Learning
An evolutionary multi-objective optimization approach to computer go controller synthesis
PRICAI'12 Proceedings of the 12th Pacific Rim international conference on Trends in Artificial Intelligence
Hi-index | 0.00 |
Go is an ancient board game that poses unique opportunities and challenges for artificial intelligence. Currently, there are no computer Go programs that can play at the level of a good human player. However, the emergence of large repositories of games is opening the door for new machine learning approaches to address this challenge. Here we develop a machine learning approach to Go, and related board games, focusing primarily on the problem of learning a good evaluation function in a scalable way. Scalability is essential at multiple levels, from the library of local tactical patterns, to the integration of patterns across the board, to the size of the board itself. The system we propose is capable of automatically learning the propensity of local patterns from a library of games. Propensity and other local tactical information are fed into recursive neural networks, derived from a probabilistic Bayesian network architecture. The recursive neural networks in turn integrate local information across the board in all four cardinal directions and produce local outputs that represent local territory ownership probabilities. The aggregation of these probabilities provides an effective strategic evaluation function that is an estimate of the expected area at the end, or at various other stages, of the game. Local area targets for training can be derived from datasets of games played by human players. In this approach, while requiring a learning time proportional to N^4, skills learned on a board of size N^2 can easily be transferred to boards of other sizes. A system trained using only 9x9 amateur game data performs surprisingly well on a test set derived from 19x19 professional game data. Possible directions for further improvements are briefly discussed.