{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:18:21Z","timestamp":1766269101764,"version":"3.37.3"},"reference-count":16,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836011"],"award-info":[{"award-number":["61836011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2018497"],"award-info":[{"award-number":["2018497"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE MultiMedia"],"published-print":{"date-parts":[[2021,7,1]]},"DOI":"10.1109\/mmul.2021.3053774","type":"journal-article","created":{"date-parts":[[2021,1,26]],"date-time":"2021-01-26T20:32:10Z","timestamp":1611693130000},"page":"117-127","source":"Crossref","is-referenced-by-count":5,"title":["State Representation Learning With Adjacent State Consistency Loss for Deep Reinforcement Learning"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3210-611X","authenticated-orcid":false,"given":"Tianyu","family":"Zhao","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4895-990X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Zhou","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"hasselt","year":"2016"},{"key":"ref11","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"article-title":"Prioritized experience replay","year":"0","author":"schaul","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"article-title":"End to end learning for self-driving cars","year":"0","author":"bojarski","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914554471"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00505"},{"article-title":"Proximal policy optimization algorithms","year":"0","author":"schulman","key":"ref4"},{"key":"ref3","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1093\/oso\/9780198538677.003.0006","article-title":"A framework for behavioural cloning","volume":"15","author":"bain","year":"0","journal-title":"Machine Intelligence"},{"key":"ref5","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","author":"wu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102924"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref9","first-page":"5639","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","author":"a","year":"0"}],"container-title":["IEEE MultiMedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/93\/9540885\/09336213.pdf?arnumber=9336213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T01:10:02Z","timestamp":1724375402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9336213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,1]]},"references-count":16,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/mmul.2021.3053774","relation":{},"ISSN":["1070-986X","1941-0166"],"issn-type":[{"type":"print","value":"1070-986X"},{"type":"electronic","value":"1941-0166"}],"subject":[],"published":{"date-parts":[[2021,7,1]]}}}