Sciweavers

209 search results - page 2 / 42
» Monte Carlo Go Has a Way to Go
Sort
View
ICGA
2008
208views Optimization» more  ICGA 2008»
13 years 5 months ago
Cross-Entropy for Monte-Carlo Tree Search
Recently, Monte-Carlo Tree Search (MCTS) has become a popular approach for intelligent play in games. Amongst others, it is successfully used in most state-of-the-art Go programs....
Guillaume Chaslot, Mark H. M. Winands, Istvan Szit...
CG
2010
Springer
13 years 3 months ago
A Human-Computer Team Experiment for 9x9 Go
Monte Carlo Tree Search has given computer go a significant boost in strength the past few years, but progress seems to have slowed, and once again we have to ask ourselves how can...
Darren Cook
CG
2008
Springer
13 years 7 months ago
Parallel Monte-Carlo Tree Search
Monte-Carlo Tree Search (MCTS) is a new best-first search method that started a revolution in the field of Computer Go. Parallelizing MCTS is an important way to increase the stren...
Guillaume Chaslot, Mark H. M. Winands, H. Jaap van...
ACG
2009
Springer
13 years 11 months ago
Evaluation Function Based Monte-Carlo LOA
Recently, Monte-Carlo Tree Search (MCTS) has advanced the field of computer Go substantially. In the game of Lines of Action (LOA), which has been dominated in the past by αβ, M...
Mark H. M. Winands, Yngvi Björnsson
CIG
2006
IEEE
13 years 11 months ago
Monte-Carlo Go Reinforcement Learning Experiments
Abstract— This paper describes experiments using reinforcement learning techniques to compute pattern urgencies used during simulations performed in a Monte-Carlo Go architecture...
Bruno Bouzy, Guillaume Chaslot