Virtual Global Search: Application to 9x9 Go
نویسنده
چکیده
Monte-Carlo simulations can be used as an evaluation function for Alpha-Beta in games. If w is the width of the search tree, d its depth, and g the number of simulations at each leaf, the total number of simulations is at least g × (2 × w 2 ). In games where moves permute, we propose to replace this algorithm by another algorithm that only needs g × 2 simulations for a similar number of games per leaf. The algorithm can also be applied to games where moves often but not always permute, such as Go. We detail its application to 9x9 Go.
منابع مشابه
Virtual Global Search: Application to 9×9 Go
Monte-Carlo simulations can be used as an evaluation function for Alpha-Beta in games. If w is the width of the search tree, d its depth, and g the number of simulations at each leaf, the total number of simulations is at least g× (2× w 2 ). In games where moves permute, we propose to replace this algorithm by another algorithm that only needs g × 2 simulations for a similar number of games per...
متن کاملAssociating Shallow and Selective Global Tree Search with Monte Carlo for 9*9 Go
This paper explores the association of shallow and selective global tree search with Monte Carlo in 9x9 go. This exploration is based on Olga and Indigo, two experimental Monte Carlo programs. We provide a min-max algorithm that iteratively deepens the tree until one move at the root is proved to be superior to the other ones. At each iteration, random games are started at leaf nodes to compute...
متن کاملMonte Carlo Go
We present an algorithm for the board game go which attempts to find the best move by simulated annealing. Remarkably, without including any go knowledge beyond the rules, our implementation leads to a playing strength of about 25 kyu on a 9x9 board.
متن کاملGrid Coevolution for Adaptive Simulations: Application to the Building of Opening Books in the Game of Go
This paper presents a successful application of parallel (grid) coevolution applied to the building of an opening book (OB) in 9x9 Go. Known sayings around the game of Go are refound by the algorithm, and the resulting program was also able to credibly comment openings in professional games of 9x9 Go. Interestingly, beyond the application to the game of Go, our algorithm can be seen as a ”meta”...
متن کاملA Linear Classifier Outperforms UCT in 9x9 Go
The dominant paradigm in computer Go is Monte-Carlo Tree Search (MCTS). This technique chooses a move by playing a series of simulated games, building a search tree along the way. After many simulated games, the most promising move is played. This paper proposes replacing the search tree with a neural network. Where previous neural network Go research has used the state of the board as input, o...
متن کامل