A Parallel Monte-Carlo Tree Search Algorithm
نویسندگان
چکیده
Monte-Carlo tree search is a powerful paradigm for the game of Go. We present a parallel Master-Slave algorithm for Monte-Carlo tree search. We experimented the algorithm on a network of computers using various configurations: from 12,500 to 100,000 playouts, from 1 to 64 slaves, and from 1 to 16 computers. On our architecture we obtain a speedup of 14 for 16 slaves. With a single slave and five seconds per move our algorithm scores 40.5% against GNUGO, with sixteen slaves and five seconds per move it scores 70.5%. We also give the potential speedups of our algorithm for various playout times.
منابع مشابه
A New Method for Parallel Monte Carlo Tree Search
In recent years there has been much interest in the Monte Carlo tree search algorithm, a new, adaptive, randomized optimization algorithm. In fields as diverse as Artificial Intelligence, Operations Research, and High Energy Physics, research has established that Monte Carlo tree search can find good solutions without domain dependent heuristics. However, practice shows that reaching high perfo...
متن کاملStructured Parallel Programming for Monte Carlo Tree Search
In this paper, we present a new algorithm for parallel Monte Carlo tree search (MCTS). It is based on the pipeline pattern and allows flexible management of the control flow of the operations in parallel MCTS. The pipeline pattern provides for the first structured parallel programming approach to MCTS. Moreover, we propose a new lock-free tree data structure for parallel MCTS which removes sync...
متن کاملA Lock-Free Multithreaded Monte-Carlo Tree Search Algorithm
With the recent success of Monte-Carlo tree search algorithms in Go and other games, and the increasing number of cores in standard CPUs, the efficient parallelization of the search has become an important issue. We present a new lock-free parallel algorithm for Monte-Carlo tree search which takes advantage of the memory model of the IA-32 and Intel-64 CPU architectures and intentionally ignore...
متن کاملParallel Monte Carlo Tree Search Scalability Discussion
In this paper we are discussing which factors affect the scalability of the parallel Monte Carlo Tree Search algorithm. We have run the algorithm on CPUs and GPUs in Reversi game and SameGame puzzle on the TSUBAME supercomputer. We are showing that the most likely cause of the scaling bottleneck is the problem size. Therefore we are showing that the MCTS is a weak-scaling algorithm. We are not ...
متن کاملMassively Parallel Monte Carlo Tree Search
Monte Carlo Tree Search is a method of finding near-optimal solutions for large state-space problems. Currently, is it very important to develop algorithms being able to take advantage of great number of processors in such areas. In this paper MCTS parallel implementations for thousand of cores are presented and discussed. The MCTS parallelization method used is the root parallelization. Implem...
متن کامل