{"id":"https://openalex.org/W3093210455","doi":"https://doi.org/10.1109/tpami.2022.3176413","title":"Masked Contrastive Representation Learning for Reinforcement Learning","display_name":"Masked Contrastive Representation Learning for Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3093210455","doi":"https://doi.org/10.1109/tpami.2022.3176413","mag":"3093210455","pmid":"https://pubmed.ncbi.nlm.nih.gov/35594229"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3176413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3176413","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028284977","display_name":"Jinhua Zhu","orcid":"https://orcid.org/0000-0003-2157-9077"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinhua Zhu","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021772140","display_name":"Yingce Xia","orcid":"https://orcid.org/0000-0001-9823-9033"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingce Xia","raw_affiliation_strings":["Microsoft Research, Beijing, 100080, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102750692","display_name":"Lijun Wu","orcid":"https://orcid.org/0000-0002-3530-590X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Wu","raw_affiliation_strings":["Microsoft Research, Beijing, 100080, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089561793","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-9624-7451"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["Electronic Engineering and Information Science, University of Science and Technology of China, 12652 Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Electronic Engineering and Information Science, University of Science and Technology of China, 12652 Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Microsoft Research, Beijing, 100080, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research, Beijing, 100080, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5028284977"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":7.9542,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97844183,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"45","issue":"3","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8088789582252502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7947699427604675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6825621724128723},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.636023759841919},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6202182769775391},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5768113136291504},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4114438593387604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3816774785518646},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32110005617141724}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8088789582252502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947699427604675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6825621724128723},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.636023759841919},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6202182769775391},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5768113136291504},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4114438593387604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3816774785518646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32110005617141724},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3176413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3176413","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35594229","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35594229","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":103,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W2064675550","https://openalex.org/W2150468603","https://openalex.org/W2158782408","https://openalex.org/W2563830277","https://openalex.org/W2575705757","https://openalex.org/W2611706523","https://openalex.org/W2626778328","https://openalex.org/W2724169821","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2794365787","https://openalex.org/W2798991696","https://openalex.org/W2842511635","https://openalex.org/W2885514323","https://openalex.org/W2890952074","https://openalex.org/W2896457183","https://openalex.org/W2900118953","https://openalex.org/W2900152462","https://openalex.org/W2902907165","https://openalex.org/W2914120296","https://openalex.org/W2920362155","https://openalex.org/W2920426271","https://openalex.org/W2922706279","https://openalex.org/W2944828972","https://openalex.org/W2949517790","https://openalex.org/W2950872548","https://openalex.org/W2951292523","https://openalex.org/W2952867909","https://openalex.org/W2962697464","https://openalex.org/W2962849838","https://openalex.org/W2962899390","https://openalex.org/W2963009616","https://openalex.org/W2963341956","https://openalex.org/W2964043796","https://openalex.org/W2964291307","https://openalex.org/W2965556524","https://openalex.org/W2970202659","https://openalex.org/W2977481643","https://openalex.org/W2982316857","https://openalex.org/W2992977009","https://openalex.org/W2994710732","https://openalex.org/W2995298643","https://openalex.org/W2996037775","https://openalex.org/W3005173720","https://openalex.org/W3009561768","https://openalex.org/W3013828496","https://openalex.org/W3015437096","https://openalex.org/W3021708257","https://openalex.org/W3023640063","https://openalex.org/W3032892481","https://openalex.org/W3034693603","https://openalex.org/W3035524453","https://openalex.org/W3036619998","https://openalex.org/W3093222659","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3098338892","https://openalex.org/W3101283005","https://openalex.org/W3103780890","https://openalex.org/W3108655343","https://openalex.org/W3115293622","https://openalex.org/W3175558129","https://openalex.org/W4287018575","https://openalex.org/W4288275971","https://openalex.org/W4292779060","https://openalex.org/W4297808394","https://openalex.org/W4298857966","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6729556111","https://openalex.org/W6731293529","https://openalex.org/W6739901393","https://openalex.org/W6740092555","https://openalex.org/W6747473740","https://openalex.org/W6749740488","https://openalex.org/W6755207826","https://openalex.org/W6756256016","https://openalex.org/W6756684005","https://openalex.org/W6759455113","https://openalex.org/W6760405395","https://openalex.org/W6765407481","https://openalex.org/W6766156693","https://openalex.org/W6768810269","https://openalex.org/W6771217966","https://openalex.org/W6772005887","https://openalex.org/W6773738434","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6775289199","https://openalex.org/W6776867236","https://openalex.org/W6778883912","https://openalex.org/W6779199192","https://openalex.org/W6779518175","https://openalex.org/W6779879114","https://openalex.org/W6780226713","https://openalex.org/W6780470247","https://openalex.org/W6784333009","https://openalex.org/W6787713516","https://openalex.org/W6800570120","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W4390516098"],"abstract_inverted_index":{"In":[0,80],"pixel-based":[1],"reinforcement":[2],"learning":[3,67,148],"(RL),":[4],"the":[5,32,73,109,119,126,150,157,167,171,180],"states":[6],"are":[7,12,50,143,174],"raw":[8],"video":[9,45,112],"frames,":[10,123],"which":[11,71],"mapped":[13],"into":[14,78],"hidden":[15,88],"representation":[16,29,66],"before":[17],"feeding":[18],"to":[19,53,107,131,156,162,176],"a":[20,48,60,84,94],"policy":[21,95,165,172],"network.":[22],"To":[23],"improve":[24,55],"sample":[25],"efficiency":[26],"of":[27,90,121,195,204],"state":[28,92],"learning,":[30],"recently,":[31],"most":[33],"prominent":[34],"work":[35],"is":[36,183,213],"based":[37,134],"on":[38,135,192],"contrastive":[39,65,147],"unsupervised":[40],"representation.":[41],"Witnessing":[42],"that":[43],"consecutive":[44,76],"frames":[46],"in":[47],"game":[49],"highly":[51],"correlated,":[52],"further":[54],"data":[56],"efficiency,":[57],"we":[58,100,116],"propose":[59],"new":[61],"algorithm,":[62],"i.e.,":[63],"masked":[64],"for":[68,87,97],"RL":[69],"(M-CURL),":[70],"takes":[72],"correlation":[74],"among":[75,111],"inputs":[77],"consideration.":[79],"our":[81],"architecture,":[82],"besides":[83],"CNN":[85,127,139,168],"encoder":[86,105,128,140,169],"presentation":[89],"input":[91],"and":[93,124,129,141,170,179,201],"network":[96,173],"action":[98],"selection,":[99],"introduce":[101],"an":[102],"auxiliary":[103],"Transformer":[104,130,142,181],"module":[106,182],"leverage":[108],"correlations":[110],"frames.":[113,137],"During":[114,164],"training,":[115],"randomly":[117],"mask":[118],"features":[120,152],"several":[122],"use":[125],"reconstruct":[132],"them":[133],"context":[136],"The":[138,211],"jointly":[144],"trained":[145],"via":[146],"where":[149],"reconstructed":[151],"should":[153],"be":[154],"similar":[155],"ground-truth":[158],"ones":[159],"while":[160],"dissimilar":[161],"others.":[163],"evaluation,":[166],"used":[175],"take":[177],"actions,":[178],"discarded.":[184],"Our":[185],"method":[186],"achieves":[187],"consistent":[188],"improvements":[189],"over":[190],"CURL":[191],"14":[193],"out":[194,203],"16":[196],"environments":[197,206],"from":[198,207],"DMControl":[199],"suite":[200],"23":[202],"26":[205],"Atari":[208],"2600":[209],"Games.":[210],"code":[212],"available":[214],"at":[215],"https://github.com/teslacool/m-curl.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}