{"id":"https://openalex.org/W4206392599","doi":"https://doi.org/10.1109/icar53236.2021.9659351","title":"Accelerated Robot Skill Acquisition by Reinforcement Learning-Aided Sim-to-Real Domain Adaptation","display_name":"Accelerated Robot Skill Acquisition by Reinforcement Learning-Aided Sim-to-Real Domain Adaptation","publication_year":2021,"publication_date":"2021-12-06","ids":{"openalex":"https://openalex.org/W4206392599","doi":"https://doi.org/10.1109/icar53236.2021.9659351"},"language":"en","primary_location":{"id":"doi:10.1109/icar53236.2021.9659351","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar53236.2021.9659351","pdf_url":null,"source":{"id":"https://openalex.org/S4363608199","display_name":"2021 20th International Conference on Advanced Robotics (ICAR)","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":"2021 20th International Conference on Advanced Robotics (ICAR)","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/A5071366153","display_name":"Zvezdan Loncarcvic","orcid":null},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]},{"id":"https://openalex.org/I4210113529","display_name":"Jo\u017eef Stefan International Postgraduate School","ror":"https://ror.org/01hdkb925","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210113529"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["SI","US"],"is_corresponding":false,"raw_author_name":"Zvezdan Loncarcvic","raw_affiliation_strings":["Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jo&#x017E","ef Stefan Institute, Ljubljana, Slovenia","Jo&#x017E","ef Stefan International Postgraduate School, Ljubljana, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jo&#x017E","institution_ids":["https://openalex.org/I4210116723"]},{"raw_affiliation_string":"ef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]},{"raw_affiliation_string":"Jo&#x017E","institution_ids":[]},{"raw_affiliation_string":"ef Stefan International Postgraduate School, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I4210113529"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019399129","display_name":"Ale\u0161 Ude","orcid":"https://orcid.org/0000-0003-3677-3972"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["SI","US"],"is_corresponding":false,"raw_author_name":"Ales Ude","raw_affiliation_strings":["Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jožef Stefan Institute, Ljubljana, Slovenia","Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jo&#x017E","ef Stefan Institute, Ljubljana, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jožef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408","https://openalex.org/I4210116723"]},{"raw_affiliation_string":"Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jo&#x017E","institution_ids":["https://openalex.org/I4210116723"]},{"raw_affiliation_string":"ef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028393702","display_name":"Andrej Gams","orcid":"https://orcid.org/0000-0002-9803-3593"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["SI","US"],"is_corresponding":false,"raw_author_name":"Andrej Gams","raw_affiliation_strings":["Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jožef Stefan Institute, Ljubljana, Slovenia","ef Stefan Institute, Ljubljana, Slovenia","Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jo&#x017E"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jožef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408","https://openalex.org/I4210116723"]},{"raw_affiliation_string":"ef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]},{"raw_affiliation_string":"Dept. of Automatics, Biocybernetics and Robotics, Humanoid and Cognitive Robotics Lab, Jo&#x017E","institution_ids":["https://openalex.org/I4210116723"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3805,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61820702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"16","issue":null,"first_page":"269","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9977999925613403,"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":0.8195717334747314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7507928609848022},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6858270168304443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6672914624214172},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6318299174308777},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6162326335906982},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5688048601150513},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49638086557388306},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4764036238193512},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4594922661781311},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.44709980487823486},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4288569986820221},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4157297611236572},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2658177614212036}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8195717334747314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507928609848022},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6858270168304443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6672914624214172},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6318299174308777},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6162326335906982},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5688048601150513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49638086557388306},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4764036238193512},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4594922661781311},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.44709980487823486},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4288569986820221},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4157297611236572},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2658177614212036},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icar53236.2021.9659351","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar53236.2021.9659351","pdf_url":null,"source":{"id":"https://openalex.org/S4363608199","display_name":"2021 20th International Conference on Advanced Robotics (ICAR)","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":"2021 20th International Conference on Advanced Robotics (ICAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1930720625","https://openalex.org/W1964985369","https://openalex.org/W1977655452","https://openalex.org/W2012392077","https://openalex.org/W2116226448","https://openalex.org/W2136719407","https://openalex.org/W2165698076","https://openalex.org/W2605102758","https://openalex.org/W2794572859","https://openalex.org/W2908261578","https://openalex.org/W2962899390","https://openalex.org/W2963390419","https://openalex.org/W2963900541","https://openalex.org/W2968116426","https://openalex.org/W2990747716","https://openalex.org/W2997896361","https://openalex.org/W3088310808","https://openalex.org/W3093922502","https://openalex.org/W3099108553","https://openalex.org/W3100789280","https://openalex.org/W3103508921","https://openalex.org/W3104876774","https://openalex.org/W3106803573","https://openalex.org/W3108357123","https://openalex.org/W3120778962","https://openalex.org/W3124270948","https://openalex.org/W3132082252"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W1484111231","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W3089231081","https://openalex.org/W2093956241","https://openalex.org/W2354420595"],"abstract_inverted_index":{"Since":[0],"robot":[1,125],"learning":[2,19,59,117,123],"takes":[3],"a":[4,66,96,112],"lot":[5],"of":[6,45,84,95,98,107,115],"time":[7],"and":[8,93],"might":[9,36],"be":[10],"too":[11],"time-consuming":[12],"to":[13,55],"perform":[14],"on":[15,70],"real":[16,91],"robots,":[17],"the":[18,27,41,46,85,99],"process":[20],"is":[21,118],"often":[22],"done":[23],"in":[24],"simulation.":[25],"Bridging":[26],"sim-to-real":[28,61],"gap,":[29],"however,":[30],"still":[31,42],"requires":[32],"real-world":[33,57,116],"effort":[34],"that":[35,111],"impose":[37],"severe":[38],"limitations":[39],"due":[40],"large":[43],"number":[44],"required":[47],"iterations.":[48],"In":[49],"this":[50],"paper":[51],"we":[52],"explore":[53],"how":[54],"accelerate":[56],"skill":[58],"with":[60,73,90,102],"transfer":[62],"learning.":[63,104],"We":[64],"propose":[65],"new":[67],"methodology":[68],"based":[69],"dimensionality":[71],"reduction":[72],"deep":[74,87],"autoencoders,":[75],"followed":[76],"by":[77,120],"domain":[78],"adaptation.":[79],"The":[80,105],"latter":[81],"combines":[82],"re-training":[83],"complete":[86],"neural":[88],"network":[89,100],"data":[92],"adaptation":[94],"part":[97],"parameters":[101],"reinforcement":[103],"results":[106],"our":[108],"experiments":[109],"demonstrate":[110],"considerable":[113],"acceleration":[114],"achieved":[119],"approach":[121],"when":[122],"complex":[124],"skills.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}