Distributed Monte Carlo Tree Search: A Novel Technique and its Application to Computer Go
Distributed Monte Carlo Tree Search: A Novel Technique and its Application to Computer Go
复制标题
DOI：
10.1109/tciaig.2014.2346997
复制
发表时间：
2015-12
影响因子：
--
通讯作者：
L. Schaefers;M. Platzner
中科院分区：
文献类型：
--
作者：
L. Schaefers;M. Platzner
近年来，Monte Carlo Tree Search（MCT）在评估随机和确定性游戏方面取得了巨大的成功。我们介绍并经验分析了针对具有Infiniband互连大型HPC簇的MCT的数据驱动的并行化方法。我们的实现基于OpenMPI，并广泛使用其基于RDMA的异步小消息通信功能，以有效地重叠通信和计算。我们将平行的MCT方法整合在我们最先进的Go Engine Gomorra中，并在现实世界中衡量其优势和局限性。我们广泛的实验表明，在自我播放实验中，我们可以扩展多达128个计算节点和2048个核心，此外，还提供了有希望的方向以进行额外改进。我们并行化方法的一般性提倡其用来显着提高大量当前MCT应用程序的搜索质量。
Monte Carlo tree search (MCTS) has brought about great success regarding the evaluation of stochastic and deterministic games in recent years. We present and empirically analyze a data-driven parallelization approach for MCTS targeting large HPC clusters with Infiniband interconnect. Our implementation is based on OpenMPI and makes extensive use of its RDMA based asynchronous tiny message communication capabilities for effectively overlapping communication and computation. We integrate our parallel MCTS approach termed UCT-Treesplit in our state-of-the-art Go engine Gomorra and measure its strengths and limitations in a real-world setting. Our extensive experiments show that we can scale up to 128 compute nodes and 2048 cores in self-play experiments and, furthermore, give promising directions for additional improvement. The generality of our parallelization approach advocates its use to significantly improve the search quality of a huge number of current MCTS applications.