{"id":"https://openalex.org/W4312335991","doi":"https://doi.org/10.1109/tcds.2022.3218940","title":"Soft Contrastive Learning With Q-Irrelevance Abstraction for Reinforcement Learning","display_name":"Soft Contrastive Learning With Q-Irrelevance Abstraction for Reinforcement Learning","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4312335991","doi":"https://doi.org/10.1109/tcds.2022.3218940"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2022.3218940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3218940","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5051746991","display_name":"Minsong Liu","orcid":"https://orcid.org/0009-0003-0822-1377"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minsong Liu","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077743639","display_name":"Luntong Li","orcid":"https://orcid.org/0000-0002-5299-4858"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luntong Li","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042335437","display_name":"Shuai Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Hao","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051746991"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.5267,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85712425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"15","issue":"3","first_page":"1463","last_page":"1473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T12676","display_name":"Machine Learning and ELM","score":0.9994000196456909,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7678595781326294},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7199761867523193},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.6416462659835815},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6208029985427856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6110470294952393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5799850225448608},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49671417474746704},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43985849618911743},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3596571087837219},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33859527111053467},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26594507694244385},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.14325791597366333}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7678595781326294},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7199761867523193},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.6416462659835815},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6208029985427856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6110470294952393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5799850225448608},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49671417474746704},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43985849618911743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3596571087837219},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33859527111053467},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26594507694244385},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.14325791597366333},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2022.3218940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3218940","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2968709009","display_name":null,"funder_award_id":"2018AAA0101005","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6023506935","display_name":null,"funder_award_id":"XDA27030400","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G800914696","display_name":null,"funder_award_id":"62136008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1844343792","https://openalex.org/W2187089797","https://openalex.org/W2397240726","https://openalex.org/W2524771588","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2842511635","https://openalex.org/W2887897884","https://openalex.org/W2887997457","https://openalex.org/W2911917164","https://openalex.org/W2913238847","https://openalex.org/W2963890729","https://openalex.org/W2994073215","https://openalex.org/W2995298643","https://openalex.org/W2996896271","https://openalex.org/W3005680577","https://openalex.org/W3007869767","https://openalex.org/W3011651653","https://openalex.org/W3034821848","https://openalex.org/W3035524453","https://openalex.org/W3080373606","https://openalex.org/W3084269620","https://openalex.org/W3089859340","https://openalex.org/W3101722615","https://openalex.org/W3108655343","https://openalex.org/W3110979110","https://openalex.org/W3125947392","https://openalex.org/W3127235394","https://openalex.org/W3129170303","https://openalex.org/W3134878008","https://openalex.org/W3166388069","https://openalex.org/W3196869853","https://openalex.org/W3213132814","https://openalex.org/W4205272462","https://openalex.org/W4205669246","https://openalex.org/W4287078276","https://openalex.org/W4287325387","https://openalex.org/W4288335419","https://openalex.org/W4297789758","https://openalex.org/W4297808394","https://openalex.org/W6638739688","https://openalex.org/W6712173889","https://openalex.org/W6741002519","https://openalex.org/W6754278344","https://openalex.org/W6756840741","https://openalex.org/W6758814384","https://openalex.org/W6763088550","https://openalex.org/W6771217966","https://openalex.org/W6771750343","https://openalex.org/W6774314701","https://openalex.org/W6774858212","https://openalex.org/W6779690080","https://openalex.org/W6779827379","https://openalex.org/W6783140480","https://openalex.org/W6787959036","https://openalex.org/W6790416196","https://openalex.org/W6790969063","https://openalex.org/W6796319466","https://openalex.org/W6798316476","https://openalex.org/W6801058317","https://openalex.org/W6803518980","https://openalex.org/W6806011949"],"related_works":["https://openalex.org/W2963177394","https://openalex.org/W2024638892","https://openalex.org/W763418848","https://openalex.org/W1595229445","https://openalex.org/W1965815883","https://openalex.org/W149041114","https://openalex.org/W4313359513","https://openalex.org/W322408318","https://openalex.org/W4362501864","https://openalex.org/W4377293004"],"abstract_inverted_index":{"The":[0,126],"difference":[1],"between":[2],"training":[3],"and":[4,74,103,111],"testing":[5],"environments":[6,132],"is":[7],"a":[8,19,24,63,72],"huge":[9],"challenge":[10],"to":[11,38,92,123],"generalizing":[12],"reinforcement":[13],"learning":[14,22,91,110],"(RL)":[15],"algorithms.":[16],"We":[17,70],"propose":[18,124],"soft":[20,108],"contrastive":[21,90,109],"with":[23,62,114],"coarser":[25,46],"approximate":[26,47],"<inline-formula":[27,48,82],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[28,49,83],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[29,50,84],"<tex-math":[30,51,85],"notation=\"LaTeX\">$Q$":[31,52,86],"</tex-math></inline-formula>":[32,53,87],"-irrelevance":[33,54],"abstraction":[34,55],"for":[35,66,89],"RL":[36,40,115,140],"(SCQRL)":[37],"increase":[39],"generalization.":[41],"Specifically,":[42],"we":[43,106],"specify":[44],"the":[45,57,60,81,98,117,137],"as":[56],"feature":[58],"of":[59,101,119],"state":[61],"theoretical":[64],"analysis":[65],"better":[67],"generalization":[68,127],"ability.":[69],"construct":[71],"positive":[73,102],"negative":[75,104],"sample":[76],"selection":[77,99],"mechanism":[78],"based":[79],"on":[80,129],"value":[88],"achieve":[93],"efficient":[94],"representation":[95],"learning.":[96],"Considering":[97],"error":[100],"samples,":[105],"design":[107],"combine":[112],"it":[113],"in":[116],"form":[118],"an":[120],"auxiliary":[121],"task":[122],"SCQRL.":[125],"experiments":[128],"several":[130],"Procgen":[131],"demonstrate":[133],"that":[134],"SCQRL":[135],"outperforms":[136],"excellent":[138],"generalized":[139],"algorithm.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
