In this work, we present a MCTS-based Go-playing program which uses convolutional networks in all parts. Our method performs MCTS in batches, explores the Monte Carlo search tree using Thompson sampling and a convolutional network, and evaluates convnet-based rollouts on the GPU. We achieve strong win rates against open source Go programs and attain competitive results against state of the art convolutional net-based Go-playing programs.
@article{arxiv.1512.03375,
title = {Convolutional Monte Carlo Rollouts in Go},
author = {Peter H. Jin and Kurt Keutzer},
journal= {arXiv preprint arXiv:1512.03375},
year = {2015}
}