Heterogeneous Multi-Task Learning of Evaluation Functions for Chess and Shogi
Heterogeneous Multi-Task Learning of Evaluation Functions for Chess and Shogi
复制标题
国际象棋和将棋评估函数的异构多任务学习
DOI：
10.1007/978-3-030-04182-3_31
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Shanchuan Wan and Tomoyuki Kaneko
中科院分区：
文献类型：
--
作者：
Haruna Sonobe;Hiroaki Nishino;Yoshihiro Okada;Kousuke Kaneko;Shanchuan Wan and Tomoyuki Kaneko
使用先进的深度学习方法，人工智能能够在玩复杂的棋盘游戏时实现前所未有的高性能。然而，在传统实践中，不同游戏的模型需要使用特定领域的数据集进行单独训练，这不利于充分利用任务之间的相关性，并且可能会导致不必要的计算资源消耗。本文提出了一种新的多任务学习框架，用于训练两种异构但相关的游戏-国际象棋和将棋的基于深度卷积神经网络的评估函数。实验结果表明，该框架的应用提高了预测精度为两个网络有限的训练步骤。
Using advanced deep learning methods, artificial intelligence is able to achieve unprecedented high performance in playing complex board games. However, in conventional practice, models for different games require separate training with domain-specific datasets, which is not conducive to enable the full use of the correlation between tasks and may cause unnecessary consumption of computing resources. This paper presents a novel multi-task learning framework for the training of deep-convolutional-neural-network-based evaluation functions for two heterogeneous but related games – chess and shogi. Experimental results show that the application of the proposed framework improved the prediction accuracy for both networks with limited training steps.