Int. J. Inf. Technol. Decis. Mak.最新文献_第3页

A Hotel Ranking Model Through Online Reviews With Aspect-Based Sentiment Analysis 基于面向方面的情感分析的在线评论酒店排名模型

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-08-24 DOI: 10.1142/s0219622022500626

Tianhui You, L. Taoa, E. Cambria

引用次数: 0

A Novel Multi-Criteria Decision-Making Approach Proposal Based On Kemira-M With Four Criteria Groups 一种基于四准则组Kemira-M的多准则决策方法

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-08-24 DOI: 10.1142/s0219622022500614

Sefacan Ay, G. Can, Pelin Toktaş

引用次数: 1

Analysis of Hyper-Parameters for AlphaZero-Like Deep Reinforcement Learning 类alphazero深度强化学习的超参数分析

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-08-19 DOI: 10.1142/s0219622022500547

Haibo Wang, M. Emmerich, M. Preuss, A. Plaat

{"title":"Analysis of Hyper-Parameters for AlphaZero-Like Deep Reinforcement Learning","authors":"Haibo Wang, M. Emmerich, M. Preuss, A. Plaat","doi":"10.1142/s0219622022500547","DOIUrl":"https://doi.org/10.1142/s0219622022500547","url":null,"abstract":"The landmark achievements of AlphaGo Zero have created great research interest into self-play in reinforcement learning. In self-play, Monte Carlo Tree Search is used to train a deep neural network, which is then used itself in tree searches. The training is gov- erned by many hyper-parameters. There has been surprisingly little research on design choices for hyper-parameter values and loss functions, presumably because of the pro- hibitive computational cost to explore the parameter space. In this paper, we investigate 12 hyper-parameters in an AlphaZero-like self-play algorithm and evaluate how these parameters contribute to training. We study them on small games, to achieve meaningful exploration with moderate computational eﬀort. The experimental results show that training is highly sensitive to hyper-parameter choices. Through multi-objective analysis, we identify 4 important hyper-parameters to further assess. To start, we ﬁnd surprising results where too much training can sometimes lead to lower performance. Our main result is that the number of self-play iterations subsumes MCTS-search sim- ulations, game episodes, and training epochs. The intuition is that these three increase together as self-play iterations increase and that increasing them individually is sub- optimal. As a consequence of our experiments, we provide recommendations on setting hyper-parameter values in self-play. The outer loop of self-play iterations should be em- phasized, in favor of the inner loop. This means hyper-parameters for the inner loop, should be set to lower values. A secondary result of our experiments concerns the choice of optimization goals, for which we also provide recommendations.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":"87 1","pages":"829-853"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80946773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Stabilization of Stochastic Exchange Rate Dynamics Under Central Bank Intervention Using Neuronets 中央银行干预下用神经网络稳定随机汇率动态

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-08-18 DOI: 10.1142/s0219622022500560

Spyridon D. Mourtas, V. Katsikis, Emmanouil Drakonakis, S. Kotsios

引用次数: 3

A Two-Phase Population and Subspace Feature-Based Multi-Classification Model to Improve Chronic Disease Diagnosis 基于两阶段种群和子空间特征的多分类模型改进慢性病诊断

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-08-18 DOI: 10.1142/s0219622022500559

Zhongdong Hua, Dian Xiao, Zheng Zhang, Hong-Yu Jia

引用次数: 0

Ranking of Classification Algorithm in Breast Cancer Based On Estrogen Receptor Using MCDM Technique 基于MCDM技术的雌激素受体乳腺癌分类算法排序

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-08-10 DOI: 10.1142/s0219622022500523

Monika Lamba, Geetika Munjal, Yogita Gigras

引用次数: 1

An Ensemble Model for Stance Detection in Social Media Texts 社交媒体文本中姿态检测的集成模型

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-08-10 DOI: 10.1142/s0219622022500481

Sara S. Sherif, D. Shawky, Hatem A. Fayed

引用次数: 0

Improvement of VIKOR Method With Application to Multi-Objective Design Problems VIKOR方法的改进及其在多目标设计问题中的应用

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-08-10 DOI: 10.1142/s0219622022500493

Lucas Falch, Clarence W. de Silva

引用次数: 3

A Deep Learning-Based Decision Support System for Mobile Performance Marketing 基于深度学习的移动绩效营销决策支持系统

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-08-01 DOI: 10.1142/s021962202250047x

Luís Miguel Matos, Paulo Cortez, R. Mendes, A. Moreau

引用次数: 0

Alternating Minimization-Based Sparse Least-Squares Classifier for Accuracy and Interpretability Improvement of Credit Risk Assessment 基于交替最小化的稀疏最小二乘分类器提高信用风险评估的准确性和可解释性

Int. J. Inf. Technol. Decis. Mak. Pub Date : 2022-07-29 DOI: 10.1142/s0219622022500444

Zhiwang Zhang, Jing He, Hui Zheng, Jie Cao, G. Wang, Yong Shi

引用次数: 2