Using Deep Convolutional Neural Networks in Monte Carlo Tree Search
University of Paderborn, Germany
Computers and Games, 2016
@article{graf2016using,
title={Using Deep Convolutional Neural Networks in Monte Carlo Tree Search},
author={Graf, Tobias and Platzner, Marco},
year={2016}
}
Deep Convolutional Neural Networks have revolutionized Computer Go. Large networks have emerged as state-of-the-art models for move prediction and are used not only as stand-alone players but also inside Monte Carlo Tree Search to select and bias moves. Using neural networks inside the tree search is a challenge due to their slow execution time even if accelerated on a GPU. In this paper we evaluate several strategies to limit the number of nodes in the search tree in which neural networks are used. All strategies are assessed using the freely available cuDNN library. We compare our strategies against an optimal upper bound which can be estimated by removing timing constraints. We show that the best strategies are only 50 ELO points worse than this upper bound.
July 11, 2016 by hgpu
