Application of MCTS in Tsumego of Computer Go
نویسندگان
چکیده
The Tsumego problem in Go was a basic and essential problem to be overcome in implementing a computer Go program. This paper proposed a reality of Monte-Carlo tree search in Tsumego of computer Go which using Monte-Carlo evaluation as an alternative for a positional evaluation function. The advantage of this technique was that it requires few domain knowledge or expert input.
منابع مشابه
Parallel Monte-Carlo tree search for HPC systems and its application to computer go
Monte-Carlo Tree Search (MCTS) is a class of simulation-based search algorithms. It brought about great success in the past few years regarding the evaluation of deterministic two-player games such as the Asian board game Go. A breakthrough was achieved in 2006, when Rémi Coulom placed 1st at the ICGA Computer Go Olympiad in Turin with his MCTS based Go programm CrazyStone in the 9× 9 devision....
متن کاملMonte Carlo Tree Search in Go
Monte Carlo Tree Search (MCTS) was born in Computer Go, i.e. in the application of artificial intelligence to the game of Go. Since its creation, in 2006, many improvements have been published. Programs are still by far weaker than the best human players, yet the gap was very significantly reduced. MCTS is now widely applied in games, in particular when no trustable evaluation function is readi...
متن کاملTowards MCTS for Creative Domains
Monte Carlo Tree Search (MCTS) has recently demonstrated considerable success for computer Go and other difficult AI problems. We present a general MCTS model that extends its application from searching for optimal actions in games and combinatorial optimisation tasks to the search for optimal sequences and embedded subtrees. The primary application of this extended MCTS model will be for creat...
متن کاملMonte-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 کاملAccelerated UCT and Its Application to Two-Player Games
Monte-Carlo Tree Search (MCTS) is a very successful approach for improving the performance of game-playing programs. This paper presents the Accelerated UCT algorithm, which overcomes a weakness of MCTS caused by deceptive structures which often appear in game tree search. It consists in using a new backup operator that assigns higher weights to recently visited actions, and lower weights to ac...
متن کامل