Learning to score final positions in the game of Go
Theoretical Computer Science - Advances in computer games
Sample-based learning and search with permanent and transient memories
Proceedings of the 25th international conference on Machine learning
Learning to predict life and death from Go game records
Information Sciences: an International Journal
Monte-Carlo tree search and rapid action value estimation in computer Go
Artificial Intelligence
Learning to estimate potential territory in the game of go
CG'04 Proceedings of the 4th international conference on Computers and Games
Hi-index | 0.00 |
The Go-playing program HONTE is described. It uses neural nets together with more conventional AI-methods like alpha-beta search. A neural net is trained by supervised learning to imitate local shapes seen in a database of expert games. A second net is trained to estimate the safety of groups by self play using a modified version of TD(λ)-learning. A third net is trained to estimate territorial potential of unoccupied points, also based on self play and TD(λ)- learning. Although the program has not yet reached the level of the most popular commercial Go-programs, results are encouraging.