{"id":"https://openalex.org/W4313535417","doi":"https://doi.org/10.1109/humanoids53995.2022.10000095","title":"Combining Reinforcement Learning and Lazy Learning for Faster Few-Shot Transfer Learning","display_name":"Combining Reinforcement Learning and Lazy Learning for Faster Few-Shot Transfer Learning","publication_year":2022,"publication_date":"2022-11-28","ids":{"openalex":"https://openalex.org/W4313535417","doi":"https://doi.org/10.1109/humanoids53995.2022.10000095"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids53995.2022.10000095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids53995.2022.10000095","pdf_url":null,"source":{"id":"https://openalex.org/S4363608580","display_name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","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 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","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/A5083969934","display_name":"Zvezdan Lon\u010darevi\u0107","orcid":"https://orcid.org/0000-0002-1233-6949"},"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"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Zvezdan Loncarevic","raw_affiliation_strings":["Jožef Stefan Institute,Humanoid and Cognitive Robotics Lab, Biocy-bernetics and Robotics,Dept. of Automatics,Ljubljana,Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jožef Stefan Institute,Humanoid and Cognitive Robotics Lab, Biocy-bernetics and Robotics,Dept. of Automatics,Ljubljana,Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049022354","display_name":"Mihael Simoni\u010d","orcid":"https://orcid.org/0000-0002-0346-7082"},"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"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Mihael Simonic","raw_affiliation_strings":["Jožef Stefan Institute,Humanoid and Cognitive Robotics Lab, Biocy-bernetics and Robotics,Dept. of Automatics,Ljubljana,Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jožef Stefan Institute,Humanoid and Cognitive Robotics Lab, Biocy-bernetics and Robotics,Dept. of Automatics,Ljubljana,Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"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"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Ales Ude","raw_affiliation_strings":["Jožef Stefan Institute,Humanoid and Cognitive Robotics Lab, Biocy-bernetics and Robotics,Dept. of Automatics,Ljubljana,Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jožef Stefan Institute,Humanoid and Cognitive Robotics Lab, Biocy-bernetics and Robotics,Dept. of Automatics,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"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Andrej Gams","raw_affiliation_strings":["Jožef Stefan Institute,Humanoid and Cognitive Robotics Lab, Biocy-bernetics and Robotics,Dept. of Automatics,Ljubljana,Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jožef Stefan Institute,Humanoid and Cognitive Robotics Lab, Biocy-bernetics and Robotics,Dept. of Automatics,Ljubljana,Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7538,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86949084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"285","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9993000030517578,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9757000207901001,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10879","display_name":"Robotic Locomotion and Control","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7933915853500366},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7859125137329102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7118538022041321},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6781941652297974},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.6691840887069702},{"id":"https://openalex.org/keywords/throwing","display_name":"Throwing","score":0.5727971792221069},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5332610011100769},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5092231035232544},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.49057334661483765},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.4834328889846802},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47918641567230225},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.47797533869743347},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4706116318702698},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45990535616874695},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3530166447162628},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.17918440699577332},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06606996059417725}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7933915853500366},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7859125137329102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7118538022041321},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6781941652297974},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6691840887069702},{"id":"https://openalex.org/C207451115","wikidata":"https://www.wikidata.org/wiki/Q12898216","display_name":"Throwing","level":2,"score":0.5727971792221069},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5332610011100769},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5092231035232544},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.49057334661483765},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4834328889846802},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47918641567230225},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.47797533869743347},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4706116318702698},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45990535616874695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3530166447162628},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.17918440699577332},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06606996059417725},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids53995.2022.10000095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids53995.2022.10000095","pdf_url":null,"source":{"id":"https://openalex.org/S4363608580","display_name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","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 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8058067020","display_name":null,"funder_award_id":"871352","funder_id":"https://openalex.org/F4320322554","funder_display_name":"Javna Agencija za Raziskovalno Dejavnost RS"}],"funders":[{"id":"https://openalex.org/F4320322554","display_name":"Javna Agencija za Raziskovalno Dejavnost RS","ror":"https://ror.org/059bp8k51"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1570792896","https://openalex.org/W1967097499","https://openalex.org/W2056114668","https://openalex.org/W2116226448","https://openalex.org/W2605102758","https://openalex.org/W2614308505","https://openalex.org/W2790705151","https://openalex.org/W2962736495","https://openalex.org/W2963092423","https://openalex.org/W2963813509","https://openalex.org/W2968116426","https://openalex.org/W2997896361","https://openalex.org/W3088310808","https://openalex.org/W3103508921","https://openalex.org/W3108357123","https://openalex.org/W3120778962","https://openalex.org/W3124270948","https://openalex.org/W3134395475","https://openalex.org/W3136347463","https://openalex.org/W3160770508","https://openalex.org/W3166655880","https://openalex.org/W3177473017","https://openalex.org/W3207033168","https://openalex.org/W3211352205","https://openalex.org/W3212380917","https://openalex.org/W3212580602","https://openalex.org/W4206392599","https://openalex.org/W4226074762","https://openalex.org/W6776458826","https://openalex.org/W6791741706","https://openalex.org/W6802778921"],"related_works":["https://openalex.org/W2757445715","https://openalex.org/W4239855920","https://openalex.org/W2371249440","https://openalex.org/W2365576545","https://openalex.org/W3165347946","https://openalex.org/W4226007727","https://openalex.org/W2059660105","https://openalex.org/W2327671128","https://openalex.org/W2386414876","https://openalex.org/W3029718387"],"abstract_inverted_index":{"Since":[0],"repeating":[1],"a":[2,5,52,64,75,82,139],"task":[3,148],"with":[4,51,63,89,175],"humanoid":[6,172],"robot":[7,159,173],"many":[8],"times":[9],"is":[10,23,60,109,149],"typically":[11],"far":[12],"too":[13],"time":[14],"consuming":[15],"and":[16,71,100,119],"strenuous":[17],"for":[18,74,165],"the":[19,29,46,131,134,144,147,154,158,170,180],"robotic":[20,137],"mechanism,":[21],"learning":[22,56,99,126,168],"often":[24],"shifted":[25],"to":[26,44,96],"simulation.":[27],"Bridging":[28],"sim-to-real":[30],"gap,":[31],"however,":[32],"still":[33],"requires":[34],"considerable":[35],"real-world":[36],"effort.":[37],"In":[38],"this":[39,85],"paper":[40],"we":[41,94],"explore":[42],"how":[43],"reduce":[45],"number":[47],"of":[48,84,117,122,136,146,157],"required":[49],"repetitions":[50],"novel":[53],"few-shot":[54],"transfer":[55,167],"methodology.":[57],"The":[58,161],"skill":[59,142],"initially":[61],"encoded":[62],"deep":[65,86],"neural":[66,87],"network":[67,88],"in":[68],"one":[69,116],"domain,":[70],"later":[72],"adapted":[73],"different":[76],"target":[77],"domain":[78],"by":[79],"re-training":[80],"only":[81,113],"partllayer":[83],"real":[90,181],"data.":[91],"For":[92],"retraining":[93],"propose":[95],"combine":[97],"lazy":[98],"reinforcement":[101],"learning.":[102],"Our":[103],"experiments":[104,162],"show":[105],"that":[106],"such":[107],"combination":[108],"considerably":[110],"faster":[111,124],"than":[112,125],"using":[114],"either":[115],"these":[118],"an":[120],"order":[121],"magnitude":[123],"from":[127],"scratch.":[128],"We":[129],"demonstrated":[130],"approach":[132],"on":[133,153,169,179],"example":[135],"throwing,":[138],"complex":[140],"dynamic":[141],"where":[143],"outcome":[145],"not":[150],"explicitly":[151],"dependent":[152],"final":[155],"position":[156],"motion.":[160],"were":[163],"performed":[164],"sim-to-sim":[166],"full-sized":[171],"TALOS,":[174],"initial":[176],"throwing":[177],"implementation":[178],"robot.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}