Sciweavers

ICGA
2007
89views Optimization» more  ICGA 2007»
13 years 4 months ago
Playing the Right Atari
We experimented a simple yet powerful optimization for Monte-Carlo Go tree search. It consists in dealing appropriately with strings that have two liberties. The heuristic is cont...
Tristan Cazenave
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...
NIPS
1993
13 years 6 months ago
Temporal Difference Learning of Position Evaluation in the Game of Go
The game of Go has a high branching factor that defeats the tree search approach used in computer chess, and long-range spatiotemporal interactions that make position evaluation e...
Nicol N. Schraudolph, Peter Dayan, Terrence J. Sej...