Improved Feature Learning: A Maximum-Average-Out Deep Neural Network for the Game Go

Author:

Li Xiali1ORCID,Lv Zhengyu1ORCID,Liu Bo1ORCID,Wu Licheng1,Wang Zheng2

Affiliation:

1. School of Information Engineering, Minzu University of China, Beijing 100081, China

2. Department of Management, Taiyuan Normal University, Shanxi 030619, China

Abstract

Computer game-playing programs based on deep reinforcement learning have surpassed the performance of even the best human players. However, the huge analysis space of such neural networks and their numerous parameters require extensive computing power. Hence, in this study, we aimed to increase the network learning efficiency by modifying the neural network structure, which should reduce the number of learning iterations and the required computing power. A convolutional neural network with a maximum-average-out (MAO) unit structure based on piecewise function thinking is proposed, through which features can be effectively learned and the expression ability of hidden layer features can be enhanced. To verify the performance of the MAO structure, we compared it with the ResNet18 network by applying them both to the framework of AlphaGo Zero, which was developed for playing the game Go. The two network structures were trained from scratch using a low-cost server environment. MAO unit won eight out of ten games against the ResNet18 network. The superior performance of the MAO unit compared with the ResNet18 network is significant for the further development of game algorithms that require less computing power than those currently in use.

Funder

National Natural Science Foundation of China

Publisher

Hindawi Limited

Subject

General Engineering,General Mathematics

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. A Nested Three-Stage Game Algorithm Based on Chess Shape Evaluation for Tibetan Jiu Chess;2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC);2024-07-02

2. Improved UCT Algorithm for WTN-EinStein Würfelt Nicht! Game Combining Domain Knowledge;2022 14th International Conference on Signal Processing Systems (ICSPS);2022-11

3. Geometry-V-Sub: An Efficient Graph Attention Network Struct Based Model for Node Classification;Applied Sciences;2022-07-19

4. Study on the Strategy of Playing Doudizhu Game Based on Multirole Modeling;Complexity;2020-10-20

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3