{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T07:19:09Z","timestamp":1760080749961,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101005"],"award-info":[{"award-number":["2018AAA0101005"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62136008"],"award-info":[{"award-number":["62136008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA27030400"],"award-info":[{"award-number":["XDA27030400"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association CAS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcds.2022.3218940","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T20:31:56Z","timestamp":1667593916000},"page":"1463-1473","source":"Crossref","is-referenced-by-count":10,"title":["Soft Contrastive Learning With Q-Irrelevance Abstraction for Reinforcement Learning"],"prefix":"10.1109","volume":"15","author":[{"given":"Minsong","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luntong","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Learning invariant representations for reinforcement learning without reconstruction","author":"zhang","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","first-page":"179","article-title":"Abstraction selection in model-based reinforcement learning","author":"jiang","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","first-page":"25502","article-title":"Why generalization in RL is difficult: Epistemic POMDPs and implicit partial observability","volume":"34","author":"ghosh","year":"2021","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","first-page":"1","article-title":"Contrastive behavioral similarity embeddings for generalization in reinforcement learning","author":"agarwal","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","first-page":"2020","article-title":"Phasic policy gradient","author":"cobbe","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","article-title":"Dream to control: Learning behaviors by latent imagination","author":"hafner","year":"2019","journal-title":"arXiv 1912 01603"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref30","article-title":"A survey of generalisation in deep reinforcement learning","author":"kirk","year":"2021","journal-title":"arXiv 2111 09794"},{"key":"ref11","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","article-title":"Cross-trajectory representation learning for zero-shot generalization in RL","author":"mazoure","year":"2021","journal-title":"arXiv 2106 02193"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3063273"},{"key":"ref32","article-title":"Hierarchical deep multi-task learning with attention mechanism for similarity learning","author":"huang","year":"2021","journal-title":"IEEE Trans Cogn Devel Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004395"},{"key":"ref1","article-title":"UNMAS: Multiagent reinforcement learning for unshaped cooperative scenarios","author":"chai","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref17","first-page":"1","article-title":"Return-based contrastive representation learning for reinforcement learning","author":"liu","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref16","first-page":"5639","article-title":"CURL: Contrastive unsupervised representation learning for reinforcement learning","author":"laskin","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref19","first-page":"2170","article-title":"DeepMDP: Learning continuous latent space models for representation learning","author":"gelada","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"8787","article-title":"Decoupling value and policy for generalization in reinforcement learning","author":"raileanu","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","first-page":"1","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref26","article-title":"Towards a unified theory of state abstraction for MDPs","volume":"4","author":"li","year":"2006","journal-title":"Proc ISAIM"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref20","first-page":"4358","article-title":"A geometric perspective on optimal representations for reinforcement learning","volume":"32","author":"bellemare","year":"2019","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411913"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207446"},{"key":"ref27","first-page":"11214","article-title":"Invariant causal prediction for block MDPs","author":"zhang","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628682"},{"key":"ref9","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","author":"cobbe","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2974509"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2614675"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST.2018.8426160"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10242607\/09939161.pdf?arnumber=9939161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:40:27Z","timestamp":1699904427000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9939161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":38,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2022.3218940","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}