零和博弈对抗中的代价函数选择与性能评价

卢向日; 汪湛清; 马宏宾

Chinese

您当前的位置：

首页 >

文章列表页 >

零和博弈对抗中的代价函数选择与性能评价

更新时间：2026-09-04

- 零和博弈对抗中的代价函数选择与性能评价
- Cost function selection and performance evaluation in Zero-sum Game confrontation
- 微电子学与计算机 2021年38卷第7期页码：30-35
- 作者机构：
  
  1. 北京理工大学自动化学院,北京,100081
  2. 复杂系统智能控制与决策国家重点实验室,北京,100081
- 作者简介：
- 基金信息：
  
  国家重点研发计划资助项目 2018AAA0101000国家重点研发计划资助项目 2017YFF0205306国家自然科学基金 61621063
- DOI：
  中图分类号：
- 纸质出版：2021
- 稿件说明：
移动端阅览
卢向日, 汪湛清, 马宏宾. 零和博弈对抗中的代价函数选择与性能评价[J]. 微电子学与计算机, 2021, 38(7): 30-35.

LU Xiangri, WANG Zhanqing, MA Hongbin. Cost function selection and performance evaluation in Zero-sum Game confrontation[J]. 2021, 38(7): 30-35.
卢向日, 汪湛清, 马宏宾. 零和博弈对抗中的代价函数选择与性能评价[J]. 微电子学与计算机, 2021, 38(7): 30-35. DOI：

LU Xiangri, WANG Zhanqing, MA Hongbin. Cost function selection and performance evaluation in Zero-sum Game confrontation[J]. 2021, 38(7): 30-35. DOI：

摘要

为了解决零和博弈(Zero-sum Game)的GAN(Generative Adversarial Networks)模型中传统对抗性神经网络的判别器损失值过高问题，改进了对抗性神经网络的代价函数.在零和博弈的非完备信息中，由于博弈对抗的生成器与判别器双方互知的MNIST数字图像信息是有限的，为了恰当的分析出博弈过程中某种因素在对抗中的作用，代价函数在零和博弈对抗神经网络中显得尤为重要.对零和博弈对抗环境中的代价函数选择与性能评价进行相关研究，进而实现获取较大优势的零和博弈.实验表明：改进型对抗性神经网络的代价函数优于传统对抗性神经网络损失函数方法.

Abstract

In order to solve the problem that the discriminator loss value of traditional adversarial neural networks in GAN (Generative Adversarial Networks) model of Zero-sum Game is too high

the cost function of adversarial neural networks is improved.In the incomplete information of the Zero-sum Game

because the MNIST digital image information than what the generator and the discriminator of the game confrontation know each other is limited

to analyze the role of certain factors in the confrontation of the gaming process

the cost function particularly important in the Generative Adversarial Networks model of Zero-sum Game. Research on the selection of cost function and performance evaluation in the confrontation environment of the Zero-sum Game

and then realize the Zero-sum Game with greater advantages. Experimental results show that the cost function of the improved Generative Adversarial Networks is better than the traditional Generative Adversarial Networks loss function method.

关键词

Keywords

references

LEE Y, CHO S. Design of semantic-based colorization of graphical user interface through conditional generative adversarial nets[J]. International Journal of Human-Computer Interaction, 2020, 36(8): 699-708. DOI:10.1080/10447318.2019.1680921.

曹志义, 牛少彰, 张继威. 基于半监督学习生成对抗网络的人脸还原算法研究[J]. 电子与信息学报, 2018, 40(2): 323-330. DOI:10.11999/JEIT170357. CAO Z Y, NIUS Z, ZHANG J W. Research on face reduction algorithm based on generative adversarial nets with semi-supervised learning[J]. Journal of Electronics and InformationTechnology, 2018, 40(2): 323-330. DOI:10.11999/JEIT170357.

LI M Y, LIU Z Q, SHI X H, et al. ATCS: auto-tuning configurations of big data frameworks based on generative adversarial nets[J]. IEEE Access, 2020, 8: 50485-50496. DOI:10.1109/ACCESS.2020.2979812.

KIMC I, KIMM, JUNGS, et al. Simplified Fréchet distance for generative adversarial nets[J]. Sensors, 2020, 20(6): 1548. DOI:10.3390/s2006 1548.

REN Y, LI S C, NIE M H, et al. Single image de-raining via improved generative adversarial nets[J]. Sensors (Basel), 2020, 20(6): 1591. DOI:10.3390/s2006 1591.

许哲豪, 陈玮. 基于生成对抗网络的图片风格迁移[J]. 软件导刊, 2018, 17(6): 207-209. DOI:10.11907/rjdk.172830. XU Z H, CHEN W. Style Transfer with generative adversarial nets[J]. Software Guide, 2018, 17(6): 207-209. DOI:10.11907/rjdk.172830.

WANG W, LIU W D, LI J, et al. A rub fault recognition method based on generative adversarial nets[J]. Journal of Mechanical Science and Technology, 2020, 34(8): 1389-1397. DOI: 1389

CHEN C Q, XIE W P, WEN Y, et al. Multiple-source domain adaptation with generative adversarial nets[J]. Knowledge-Based Systems, 2020(199): 105962. DOI:10.1016/j.knosys.2020. 105962.

张营营. 生成对抗网络模型综述[J]. 电子设计工程, 2018, 26(5): 34-37. DOI:10.3969/j.issn.1674-6236.2018.05.007. ZHANG YY. A survey on generative adversarial networks[J]. Electronic Design Engineering, 2018, 26(5): 34-37. DOI:10.3969/j.issn.1674-6236.2018.05.007.

GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2014: 2672-2680.

REN Y, LIS C, NIEM H, et al. Single image de-raining via improved generative adversarial nets[J]. Sensors (Basel), 2020, 20(6): 1591. DOI:10.3390/s2006 1591.

林嘉豪, 章宗长, 姜冲, 等. 基于生成对抗网络的模仿学习综述[J]. 计算机学报, 2020, 43(2): 326-351. DOI:10.11897/SP.J.1016.2020.00 326. LIN J H, ZHANG Z C, JIANGC, et al. A survey of imitation learning based on generative adversarial nets[J]. Chinese Journal of Computers, 2020, 43(2): 326-351. DOI:10.11897/SP.J.1016.2020.00 326.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向处理器分支预测单元的Spectre攻击轻量化防御方法

超低功耗实时时钟电路的设计

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

基于监控指标关联性的微服务异常检测

基于区块链的AI生成内容溯源框架设计研究