{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T14:38:32Z","timestamp":1764859112170,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61203192"],"award-info":[{"award-number":["61203192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK2011124"],"award-info":[{"award-number":["BK2011124"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2914469","type":"journal-article","created":{"date-parts":[[2019,5,2]],"date-time":"2019-05-02T19:52:57Z","timestamp":1556826777000},"page":"57069-57077","source":"Crossref","is-referenced-by-count":19,"title":["Learning to Learn: Hierarchical Meta-Critic Networks"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0996-436X","authenticated-orcid":false,"given":"Zhixiong","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiliang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1080\/1028415X.2016.1231438"},{"key":"ref33","first-page":"1589","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref32","first-page":"2568","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1007\/BF00992698"},{"key":"ref30","first-page":"2113","article-title":"Gradient-based hyperparameter optimization through reversible learning","author":"maclaurin","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref37","first-page":"38","article-title":"Distilling the knowledge in a neural network","volume":"14","author":"hinton","year":"2015","journal-title":"Comput Sci"},{"key":"ref36","first-page":"173","article-title":"Error decorrelation: A technique for matching a class of functions","author":"donaldson","year":"1960","journal-title":"Proc 3rd Int Conf Med Electron"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1007\/978-1-4842-2766-4_12"},{"year":"2017","author":"sung","journal-title":"Learning to learn Meta-critic networks for sample efficient learning","key":"ref34"},{"key":"ref10","first-page":"3486","article-title":"Strategic attentive writer for learning macro-actions","author":"vezhnevets","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref11","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"year":"2017","author":"florensa","journal-title":"Stochastic neural networks for hierarchical reinforcement learning","key":"ref12"},{"key":"ref13","first-page":"456","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"year":"2017","author":"levy","journal-title":"Learning multi-level hierarchies with hindsight","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref16","first-page":"271","article-title":"Feudal reinforcement learning","author":"dayan","year":"1992","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"year":"2017","author":"ghazanfari","journal-title":"Autonomous extracting a hierarchical structure of tasks in reinforcement learning and multi-task reinforcement learning","key":"ref17"},{"key":"ref18","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1023\/A:1019956318069"},{"key":"ref28","first-page":"458","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"year":"2016","author":"wang","journal-title":"Learning to reinforcement learn","key":"ref4"},{"key":"ref27","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1017\/S0140525X16001837"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/978-1-4615-5529-2_1"},{"key":"ref29","first-page":"523","article-title":"Learning feed-forward one-shot learners","author":"bertinetto","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref5","first-page":"1","article-title":"Simple principles of metalearning","volume":"69","author":"schmidhuber","year":"1996","journal-title":"Technical Report IDSIA"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1016\/S0004-3702(99)00052-1"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TSMCC.2012.2218595"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1038\/nature16961"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1007\/s10994-016-5580-x"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1038\/nature14236"},{"key":"ref20","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref22","first-page":"2402","article-title":"Meta-gradient reinforcement learning","author":"xu","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"year":"2017","author":"al-shedivat","journal-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","key":"ref21"},{"key":"ref24","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","author":"santoro","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref23","first-page":"1","article-title":"Atari games and intel processors","author":"adamski","year":"2017","journal-title":"Proc Comput Games Workshop"},{"year":"2017","author":"mishra","journal-title":"A simple neural attentive meta-learner","key":"ref26"},{"year":"2016","author":"duan","journal-title":"RL2 Fast reinforcement learning via slow reinforcement learning","key":"ref25"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08704874.pdf?arnumber=8704874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:40:21Z","timestamp":1628624421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8704874\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2914469","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}