{“状态”:“确定”,“消息类型”:“工作”,“信息版本”:“1.0.0”,“邮件”:{“索引”:{“日期-部分”:[[2024,5,10]],“日期-时间”:“2024-05-10T06:27:21Z”,“时间戳”:1715322441649},“引用-计数”:0,“发布者”:“人工智能发展协会(AAAI)”,“问题”:“1”,“内容域”:{“域”:[],“交叉标记限制”:false},“short container-title”:[“AAAI”],“抽象”:“\该摘要提出了一种时间序列异常检测器,它1)不假设异常模式的潜在机制,2)避免了在特定场景下设置阈值以获得良好异常检测性能的繁琐工作,3)随着异常检测经验的增长而不断发展。异常检测器本质上是由递归神经网络(RNN)提供动力,并采用强化学习(RL)方法实现自学习过程。我们的初步实验证明了在网络时间序列异常检测问题中使用检测器的有希望的结果。\n\n<\/jats:p>“,”DOI“:”10.1609\/aaai.v32i1.12130“,”type“:”journal-article“,”created“:{”date-parts“:[2022,6,21]],”date-time“:”2022-06-21T20:14:30Z“,”timestamp“:1655842470000},”source“:“Crossref”,“is-referenced-by-count”:33,”title“:[”Towards Experienced Anomaly Detector Through Reinforcement Learning“],”prefix“:”101609“,”volume“:“32”,“作者“:[{”给定“:”成强“,”家庭“:”黄“,”序列“:”第一“,”从属“:[]},{”给出“:”玉磊“,”家族“:”吴“,”顺序“:”附加“,”隶属“:[]},,{给定“:{“给定”:“戈永”,“家族”:“敏”,“序列”:“additional“,”affiliation“:[]}],”member“:”9382“,”published-on-line“:{”date-parts“:[[2018,4,29]]},”container-title“:[”AAAI人工智能会议记录“],”original-title”:[],“link”:[{“URL”:“https:\/\/ojs.AAAI.org\/index.php\/AAAAI\/article\/download\/12130\/11989”,“content-type”:“application\/pdf”,“content-version”:“vor”,“intended-application“:”text-mining“},{”URL“:”https:\/\/ojs.aaai.org\/index.php\/aaai\/aarticle\/download\/12130\/11899“,”content-type“:”unspecified“,”content-version“:”vor“,”intended-application”:“similarity-checking”}],“deposed”:{“date-parts”:[2022,11,7]],“date-time”:“2022-11-07T18:04:59Z”,“timestamp”:1667844299000},“分数”:1,“资源”:{primary“:{”URL“:”https:\/\/ojs.aaai.org\/index.php\/aaai\/article\/view\/12130“}},”subtitle“:[],”shorttitle“:[],”issued“:{date-parts”:[[2018,4,29]]},“references-count”:0,“journal-issue”:{“issue”:“1”,“published-online”:{date-parts“:[2018,2,8]]}}”,“URL”:“http://\”/dx.doi.org \/10.10609 \/aaai.v32i1.12130“,”关系“:{},”ISSN“:[”2374-3468“,”2159-5399“],“issn-type”:[{“value”:“2374-3468”,“type”:“electronic”},{“value”:“2159-5399”,“type”:“print”}],“subject”:[],“published”:{“date parts”:[[2018,4,29]]}}