Combining Tactical Search and Monte-Carlo in the Game of Go
نویسندگان
چکیده
We present a way to integrate search and Monte-Carlo methods in the game of Go. Our program uses search to find the status of tactical goals, builds groups, selects interesting goals, and computes statistics on the realization of tactical goals during the random games. The mean score of the random games where a selected tactical goal has been reached and the mean score of the random games where it has failed are computed. They are used to evaluate the selected goals. Experimental results attest that combining search and Monte-Carlo significantly improves the playing level.
منابع مشابه
Monte-Carlo Tree Search Solver
Recently, Monte-Carlo Tree Search (MCTS) has advanced the field of computer Go substantially. In this article we investigate the application of MCTS for the game Lines of Action (LOA). A new MCTS variant, called MCTS-Solver, has been designed to play narrow tactical lines better in sudden-death games such as LOA. The variant differs from the traditional MCTS in respect to backpropagation and se...
متن کاملGoGoGo: Improving Deep Neural Network Based Go Playing AI with Residual Networks
The game of Go has a long history and has been viewed as the most challanging classical game due to the enormous amount of possible moves and the lack of precise evaulation tools. AlphaGo [13], a Go-playing AI built by Google DeepMind, used a new approach of combining deep neural networks with tree search to solve the Go playing problem. It narrows down the search space by introducing ”policy n...
متن کاملMonte-Carlo Approximation of Temperature
Monte-Carlo tree search is a powerful paradigm for the game of Go. We propose to use Monte-Carlo tree search to approximate the temperature of a game, using the mean result of the playouts. Experimental results on the sum of five 7x7 Go games show that it improves much on a global search algorithm.
متن کاملOn Semeai Detection in Monte-Carlo Go
A frequently mentioned limitation of Monte-Carlo Tree Search (MCTS) based Go programs is their inability to recognize and adequately handle capturing races, also known as semeai, especially when many of them appear simultaneously. The inability essentially stems from the fact that certain group status evaluations require deep lines of correct tactical play which is directly related to the explo...
متن کاملMemory-Augmented Monte Carlo Tree Search
This paper proposes and evaluates Memory-Augmented Monte Carlo Tree Search (M-MCTS), which provides a new approach to exploit generalization in online realtime search. The key idea of M-MCTS is to incorporate MCTS with a memory structure, where each entry contains information of a particular state. This memory is used to generate an approximate value estimation by combining the estimations of s...
متن کامل