{"id":"https://openalex.org/W3176365423","doi":"https://doi.org/10.1109/icra46639.2022.9812213","title":"Intrinsically Motivated Self-supervised Learning in Reinforcement Learning","display_name":"Intrinsically Motivated Self-supervised Learning in Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W3176365423","doi":"https://doi.org/10.1109/icra46639.2022.9812213","mag":"3176365423"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812213","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5062078743","display_name":"Yue Zhao","orcid":"https://orcid.org/0000-0002-4007-7016"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210161752","display_name":"Beijing Haidian Hospital","ror":"https://ror.org/058x5eq06","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210161752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Zhao","raw_affiliation_strings":["Peking University,Haidian, Beijing,China","Peking University, Haidian, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University,Haidian, Beijing,China","institution_ids":["https://openalex.org/I4210161752","https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I4210161752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044355459","display_name":"Chenzhuang Du","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenzhuang Du","raw_affiliation_strings":["Tsinghua University,Haidian, Beijing,China","Tsinghua University, Haidian, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Haidian, Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104009095","display_name":"Hang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["Tsinghua University,Haidian, Beijing,China","Tsinghua University, Haidian, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Haidian, Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107678752","display_name":"Tiejun Li","orcid":"https://orcid.org/0000-0002-5400-4395"},"institutions":[{"id":"https://openalex.org/I4210161752","display_name":"Beijing Haidian Hospital","ror":"https://ror.org/058x5eq06","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210161752"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Li","raw_affiliation_strings":["Peking University,Haidian, Beijing,China","Peking University, Haidian, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University,Haidian, Beijing,China","institution_ids":["https://openalex.org/I4210161752","https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I4210161752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062078743"],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210161752"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.36387632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3605","last_page":"3615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9491000175476074,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9064396619796753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7620334625244141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7374228835105896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7002604007720947},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6524662971496582},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.48954686522483826},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4421716332435608},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4385963976383209},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4355859160423279},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13708364963531494},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1296326220035553}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9064396619796753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7620334625244141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7374228835105896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7002604007720947},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6524662971496582},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.48954686522483826},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4421716332435608},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4385963976383209},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4355859160423279},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13708364963531494},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1296326220035553},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9812213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812213","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1988526405","https://openalex.org/W2145339207","https://openalex.org/W2604373826","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2842511635","https://openalex.org/W2885550588","https://openalex.org/W2899205164","https://openalex.org/W2950794298","https://openalex.org/W2962902376","https://openalex.org/W2963009616","https://openalex.org/W2963276097","https://openalex.org/W2964067469","https://openalex.org/W2977481643","https://openalex.org/W3005680577","https://openalex.org/W3034978746","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3041404693","https://openalex.org/W3107359931","https://openalex.org/W3107668149","https://openalex.org/W3115293622","https://openalex.org/W3126321819","https://openalex.org/W3134652006","https://openalex.org/W3171007011","https://openalex.org/W3175182975","https://openalex.org/W3205321526","https://openalex.org/W3208212324","https://openalex.org/W4287393217","https://openalex.org/W4287599290","https://openalex.org/W4297808394","https://openalex.org/W6607097208","https://openalex.org/W6717230150","https://openalex.org/W6731293529","https://openalex.org/W6735865323","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6753925943","https://openalex.org/W6756303580","https://openalex.org/W6768511085","https://openalex.org/W6774314701","https://openalex.org/W6775634482","https://openalex.org/W6779326418","https://openalex.org/W6781203905","https://openalex.org/W6784862516","https://openalex.org/W6786133796","https://openalex.org/W6786614245","https://openalex.org/W6788031615","https://openalex.org/W6791742336","https://openalex.org/W6797309367","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W3148060700","https://openalex.org/W2794908468","https://openalex.org/W2531570999","https://openalex.org/W2042184006","https://openalex.org/W4319302697","https://openalex.org/W2921630034","https://openalex.org/W4390062853","https://openalex.org/W2062926306","https://openalex.org/W4310801741","https://openalex.org/W4317542939"],"abstract_inverted_index":{"In":[0],"vision-based":[1,138],"reinforcement":[2,109],"learning":[3,42,76,79,110],"(RL)":[4],"tasks,":[5,56],"it":[6],"is":[7,151],"prevalent":[8],"to":[9,20,64],"assign":[10],"auxiliary":[11,34,55,113],"tasks":[12,35,140],"with":[13,111,115,121],"a":[14,59],"surrogate":[15],"self-supervised":[16,33,66,86,112],"loss":[17,67,87],"so":[18],"as":[19,68,91],"obtain":[21],"more":[22],"semantic":[23],"representations":[24],"and":[25,44,96,134],"improve":[26],"sample":[27,132],"efficiency.":[28],"However,":[29],"abundant":[30],"information":[31,53],"in":[32,54,77,136],"has":[36],"been":[37],"disregarded,":[38],"since":[39],"the":[40,45,85,123,142,148],"representation":[41],"part":[43,47],"decision-making":[46],"are":[48],"separated.":[49],"To":[50],"sufficiently":[51],"utilize":[52],"we":[57],"present":[58],"simple":[60],"yet":[61],"effective":[62],"idea":[63],"employ":[65],"an":[69],"intrinsic":[70],"reward,":[71],"called":[72],"Intrinsically":[73],"Motivated":[74],"Self-Supervised":[75],"Reinforcement":[78],"(IM-SSR).":[80],"We":[81],"formally":[82],"show":[83],"that":[84],"can":[88,103],"be":[89,104],"decomposed":[90],"exploration":[92],"for":[93],"novel":[94],"states":[95],"robustness":[97],"improvement":[98],"from":[99,141],"nuisance":[100],"elimination.":[101],"IM-SSR":[102],"effortlessly":[105],"plugged":[106],"into":[107],"any":[108],"objectives":[114],"nearly":[116],"no":[117],"additional":[118],"cost.":[119],"Combined":[120],"IM-SSR,":[122],"previous":[124],"underlying":[125],"algorithms":[126],"achieve":[127],"salient":[128],"improvements":[129],"on":[130],"both":[131],"efficiency":[133],"generalization":[135],"various":[137],"robotics":[139],"DeepMind":[143],"Control":[144],"Suite,":[145],"especially":[146],"when":[147],"reward":[149],"signal":[150],"sparse.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}