发布求助
文献互助 智能选刊 最新文献

2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)最新文献

筛选
英文 中文
Decaying Clipping Range in Proximal Policy Optimization 近端策略优化中的衰减裁剪范围
2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2021-02-20 DOI: 10.1109/SACI51354.2021.9465602
M'onika Farsang, Luca Szegletes
{"title":"Decaying Clipping Range in Proximal Policy Optimization","authors":"M'onika Farsang, Luca Szegletes","doi":"10.1109/SACI51354.2021.9465602","DOIUrl":"https://doi.org/10.1109/SACI51354.2021.9465602","url":null,"abstract":"Proximal Policy Optimization (PPO) is among the most widely used algorithms in reinforcement learning, which achieves state-of-the-art performance in many challenging problems. The keys to its success are the reliable policy updates through the clipping mechanism and the multiple epochs of minibatch updates. The aim of this research is to give new simple but effective alternatives to the former. For this, we propose linearly and exponentially decaying clipping range approaches throughout the training. With these, we would like to provide higher exploration at the beginning and stronger restrictions at the end of the learning phase. We investigate their performance in several classical control and locomotive robotic environments. During the analysis, we found that they influence the achieved rewards and are effective alternatives to the constant clipping method in many reinforcement learning tasks.","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133005002","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: 2
Feature Learning for Accelerometer based Gait Recognition 基于加速度计的特征学习步态识别
2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 2020-07-31 DOI: 10.1109/SACI51354.2021.9465576
Szilárd Nemes, M. Antal
{"title":"Feature Learning for Accelerometer based Gait Recognition","authors":"Szilárd Nemes, M. Antal","doi":"10.1109/SACI51354.2021.9465576","DOIUrl":"https://doi.org/10.1109/SACI51354.2021.9465576","url":null,"abstract":"Recent advances in pattern matching, such as speech or object recognition support the viability of feature extraction with deep learning solutions for gait recognition. Past papers have evaluated convolutional neural networks for this task, while this work focuses on how autoencoders perform in this context. A biometric pipeline was implemented that is capable of identification when presented with step cycles, while also performing feature extraction that employ autoencoders of various configurations. The results obtained from the ZJU-GaitAcc dataset show that fully convolutional autoencoders are able to learn good representation from any type of gait segment. Measurements also show that representation learning works even better when it is incorporated into an end-to-end model of a discriminative classifier.","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127936482","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: 5
[Copyright notice] (版权)
2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 1900-01-01 DOI: 10.1109/saci51354.2021.9465565
{"title":"[Copyright notice]","authors":"","doi":"10.1109/saci51354.2021.9465565","DOIUrl":"https://doi.org/10.1109/saci51354.2021.9465565","url":null,"abstract":"","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115932926","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
[SACI 2021 Front cover] [SACI 2021封面]
2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) Pub Date : 1900-01-01 DOI: 10.1109/saci51354.2021.9465581
{"title":"[SACI 2021 Front cover]","authors":"","doi":"10.1109/saci51354.2021.9465581","DOIUrl":"https://doi.org/10.1109/saci51354.2021.9465581","url":null,"abstract":"","PeriodicalId":321907,"journal":{"name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123541543","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
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信