{“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”:[[2024,6,22]],“日期时间”:“2024-06-22T18:39:43Z”,“时间戳”:1719081583799},“参考计数”:28,“出版商”:“电气与电子工程师学会(IEEE)”,“问题”:“3”,“许可证”:[{“开始”:{-date-parts”:[2019,9,1]],“日期-时间”:“2019-09-01T00:00:00Z”,“timestamp”:1567296000000},“content-version”:“vor”,“delay-in-days”:0,“URL”:“https:\/\/ieeexplore.iee.org\/Xplorehelp\/downloads\/license-information\/ieee.html”},{“start”:{“date-parts”:[2019,9,1]],“date-time”:“2019-10-01T00:00Z”,”timestamp“:1567299600000}”,“content-Verss ion“:”stm-asf“,”delay-in-days“:0,”URL“:“https:\/\/doi.org\/10.15223\/policy-029”},{“start”:{“date-parts”:[[2019,9,1]],“date-time”:“2019-09-01T00:00:00Z”,“timestamp”:1567296000000},“content-version”:“stm-asf”,“delay-in-days”:0,“URL”:“http:\//doi.org\/10.15.223\/plicy-037”}],“出资人”:[{“name”:“国土部”“韩国政府基础设施和交通”,“奖项”:[“18TLRPB101406-04”]},{“name”:“韩国贸易工业和能源部MOTIE”,“award”:[“10079730”]}],“content-domain”:{“domain”:[],“crossmark-restriction”:false},“short-container-title”:[”IEEE Trans.Intell.Veh.“],“published-print”:{“date-parts”:[[2019,9]}”,“DOI”:“10.1109\/tiv.2019.2919467”,“type”:“”journal-article“,”created“:{”date-parts“:[[2019,5,28]],“日期-时间”:“2019-05-28T19:48:05Z”,“时间戳”:1559072885000},“页面”:“416-424”,“源”:“Crossref”,“is-referenced-by-count”:53,“标题”:[“基于深度分布强化学习的高级驾驶策略确定”],“前缀”:“10.1109”,”卷“:”4“作者”:[{“ORCID”:“http://\ORCID.org\/00000-0002-8506-1077”,“authenticated-orcid”:false,“given”:“Kyushik”,“family”:“Min”,“sequence”:“first”,“affiliation”:[]},{“orcid”:”http://\/orcid.org\/00000-0003-0290-5121“,”authentimated-orcid“:false”,“giving”:“Hayoung”,“家族”:“Kim”,“序列”:“additional”,“abliation”ted-orcid“:false,”given“:”Kunsoo“,“family”:“Huh”,“sequence”:“additional”,“affiliation”:[]}],“member”:“263”,“reference”:[{“key”:“ref10”,“article-title”:“distribution reinforction learning with quantile regression”,“author”:“dabney”,“year”:“2017”},{“key”:“ref11”,“article-title”:“Distribution erence reinforcing with quantile regession”,”author“dabne”,“年份”:“0”,“journal-title”:“Proc 30nd AAAI Conf Artif Intell”},{“key”:“ref12”,“doi-asserted-by”:“publisher”,“doi”:“10.23919\/ACC.2017.7963716”}、{“密钥”:“ref13”,“doi-asserte-by”:“publisher”,“DI:”10.1109\/IVS.2017.795709“},}“key:”ref14“,”doi-assert-by“:”publisher“,”doi“:”10.1109\/IVS.2017.7995703“},{“key”:“ref15”,“doi-asserted-by”:“publisher”,“doi”:“10.1109\/CVPR.2015.7298594”},{“key”:“ref16”,“doi-asserted-by”:“publisher”,“doi”:“10.2352\/ISSN.2470-1173.2017.19.AVM-023”}:“安全、多智能体、自动驾驶强化学习”,“作者”:“shalev-shwartz”,“年份”:“2016”},{“关键”:“参考19”,“文章标题”:“使用神经网络的机器人强化学习”、“作者”:“林”,“年”:“1993”}、{“密钥”:“ref28”,“论文标题”:”Unity:智能体的通用平台“,”author“:”juliani“,”年份“:”2018“}:“ref4”,“article-title”:“DeepMind将谷歌数据中心冷却费用降低40%”,“年份”:“2016年”},{“key”:“ref27”,“首页”:“249”,“article-title”:“了解深度前馈神经网络训练的难度”,“author”:“glorot”,“year”:“0”,“journal-title“:”Proc 13th Int Conf Artif Intell Statist“},}“key:”:“ref3”,“doi-asserted-by”:“crossref”,“first page”:“529”,“DOI”:“10.1038\/nature14236”,“article-title”:“通过深度强化学习进行人性化控制”,“volume”:《518》,“author”:“mnih”,“year”:“2015”,“journal title”:《Nature》},{“key”:,“journal-title”:“Proc-Adv Neural Inform Process Syst”},{“key”:“ref5”,“doi-asserted-by”:“publisher”,“doi”:“10.1109\/ICRA.2016.7487173”}:“舒尔曼”,“年份”:“0”,“日志标题”:“Proc Int Conf Mach Learn”},{“key”:“ref2”,“doi-asserted-by”:“crossref”,“首页”:“354”,“doi”:“10.1038\/nature24270”,“article-title”:“在没有人类知识的情况下掌握围棋游戏”,“volume”:”550“author”:“silver”,“year”:“2017”,“journal-title“:”Nature“},”{“密钥”:“ref9”,“第一页”:“449”,“article-title”:“强化学习的分布视角”,“author”:“bellemare”,“year”:“0”,“journal-title”:“Proc 34th Int Conf Mach Learn-Volume”},{“key”:“ref1”,“doi-asserted-by”:“crossref”,“first page”:《484》,“doi”:“10.1038\/nature16961”,“article-title“掌握深度神经网络和树搜索的围棋游戏”,“Volume”::“silver”,“year”:“2016”,“journal-title”:“Nature”},{“key”:“ref20”,“first-page”:“2094”,“article-title“:“双q学习的深度强化学习”,“volume”:”2“,”author“:”van hasselt“,”year“:”0:“深度强化学习的决斗网络架构”,“卷”:“48”,“作者”:“王”,“年份”:“0”,“日志标题”:“第33届国际会议机器学习”},{“密钥”:“ref21”,“首页”:“2613”,“文章标题”:”双q-learning“,”作者“:”hasselt“,”年份“:”0“,”日志标题“:”Proc Adv Neural Inf Process Syst“},”{“key”:“ref24”,“doi-asserted-by”:“publisher”,“DOI”:“10.1162\/neco.1997.9.81735”},{“key”:“ref23”,“DOI asserted by”:“publisher”,“DOI”:“10.1257\/jep.15.4.143”},{“key”:“ref26”,“文章标题”:“Adam:随机优化方法”,“author”:“kingma”,“year”:“2015”,“journal title”:“Proc Int Conf Learn Represent”},{“key”:“ref25”,“first page”:“265”,“文章标题”:“Tensorflow:大规模机器学习系统。”,“volume”:“16”,“author”:“abadi”,“year”:“0”,“journal-title”:“Proc 10th USENIX Conf Oper Syst Des Implementation”}],“container-title“:[”IEEE Transactions on Intelligent Vehicles“],“original-tittle”:[],“link”:[{“URL”:“http://\explorestaging.iee.org\/ielx7\/72748857\/881310\/08723635.pdf?arnumber=8723635“,”content-type“:”unspecified“,”content-version“:”vor“,”intended-application“:”similarity-checking“}],”deposed“:{”date-parts“:[2022,7,13]],”date-time“:“2022-07-13T21:13:47Z”,”timestamp“:1657746827000},”score“:1,”resource“:”{“primary”:{“URL”:“https:\\ieeexplore.iee.org\/document\/8723635\/”}},“副标题”:[],“短标题”:[],“发布“:{“date-parts”:[[2019,9]]},“references-count”:28,“journal-issue”:{”issue“:”3“},”URL“:”http://\/dx.doi.org\/10.109\/tiv.2019.2919467“,”relationship“:{},‘ISSN’:[”2379-8904“,”2379-9858“],‘ISSN-type’:[{“value”:“2379-89004”,“type”:”electronic“}“,”type“:”print“}],”subject“:[],”published“:{”date-parts“:[[2019,9]]}}