{"id":"https://openalex.org/W4395664827","doi":"https://doi.org/10.1109/amc58169.2024.10505631","title":"Human-in-the-Loop Training Leads to Faster Skill Acquisition and Adaptation in Reinforcement Learning-Based Robot Control","display_name":"Human-in-the-Loop Training Leads to Faster Skill Acquisition and Adaptation in Reinforcement Learning-Based Robot Control","publication_year":2024,"publication_date":"2024-02-28","ids":{"openalex":"https://openalex.org/W4395664827","doi":"https://doi.org/10.1109/amc58169.2024.10505631"},"language":"en","primary_location":{"id":"doi:10.1109/amc58169.2024.10505631","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/amc58169.2024.10505631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Advanced Motion Control (AMC)","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/A5032046594","display_name":"Deniz Yilmaz","orcid":"https://orcid.org/0000-0002-6444-1644"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Deniz Yilmaz","raw_affiliation_strings":["Ozyegin University,Dept. of Computer Science,Istanbul,Türkiye"],"affiliations":[{"raw_affiliation_string":"Ozyegin University,Dept. of Computer Science,Istanbul,Türkiye","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080517829","display_name":"Barkan U\u011furlu","orcid":"https://orcid.org/0000-0002-9124-7441"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Barkan Ugurlu","raw_affiliation_strings":["Ozyegin University,Dept. of Mechanical Engineering,Istanbul,Türkiye"],"affiliations":[{"raw_affiliation_string":"Ozyegin University,Dept. of Mechanical Engineering,Istanbul,Türkiye","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018729334","display_name":"Erhan \u00d6ztop","orcid":"https://orcid.org/0000-0002-3051-6038"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Erhan Oztop","raw_affiliation_strings":["Ozyegin University,Dept. of Computer Science,Türkiye"],"affiliations":[{"raw_affiliation_string":"Ozyegin University,Dept. of Computer Science,Türkiye","institution_ids":["https://openalex.org/I44925452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032046594"],"corresponding_institution_ids":["https://openalex.org/I44925452"],"apc_list":null,"apc_paid":null,"fwci":0.3297,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52641643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9914000034332275,"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":0.9914000034332275,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9850999712944031,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9811000227928162,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8072099685668945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6792248487472534},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6728634238243103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5456420183181763},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5077767968177795},{"id":"https://openalex.org/keywords/dreyfus-model-of-skill-acquisition","display_name":"Dreyfus model of skill acquisition","score":0.4516753554344177},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4442346394062042},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.43926623463630676},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4178413450717926},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.33362704515457153},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1589573621749878},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.13713890314102173}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8072099685668945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6792248487472534},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6728634238243103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5456420183181763},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5077767968177795},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.4516753554344177},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4442346394062042},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.43926623463630676},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4178413450717926},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33362704515457153},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1589573621749878},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.13713890314102173},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/amc58169.2024.10505631","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/amc58169.2024.10505631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Advanced Motion Control (AMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1517823811","https://openalex.org/W2028411224","https://openalex.org/W2049410986","https://openalex.org/W2129659607","https://openalex.org/W2290053245","https://openalex.org/W2604382266","https://openalex.org/W2736601468","https://openalex.org/W2779458783","https://openalex.org/W2797333641","https://openalex.org/W2898227854","https://openalex.org/W3024350433","https://openalex.org/W3039116038","https://openalex.org/W3046700210","https://openalex.org/W3184240110","https://openalex.org/W3192495122","https://openalex.org/W3195968524","https://openalex.org/W4383503699","https://openalex.org/W6696265566","https://openalex.org/W6740033195","https://openalex.org/W6750568380"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,71,83,122,155],"training":[4,17,97,103,166,175],"procedure":[5],"for":[6,59],"reinforcement":[7,91],"learning-based":[8],"robot":[9,85,113,152],"control":[10,158],"to":[11,36,114,118,125,161],"achieve":[12],"skill":[13,88],"acquisition":[14,89],"with":[15,74,144],"reduced":[16,174],"time":[18,176],"and":[19,105,177],"data":[20,178],"requirements.":[21],"It":[22],"achieves":[23],"this":[24,81],"by":[25,39],"actively":[26],"incorporating":[27],"the":[28,40,44,47,50,53,65,68,112,116,119,135,164],"actions":[29,37,55],"provided":[30],"via":[31,90],"human":[32,54,146],"inputs":[33],"in":[34,93,134,154,171],"addition":[35],"generated":[38],"learning":[41,92,153],"algorithm.":[42],"As":[43],"algorithm":[45],"acquires":[46],"target":[48],"skill,":[49],"contribution":[51],"of":[52,67,121,137,173],"is":[56],"gradually":[57],"decreased":[58],"autonomous":[60,107,162],"task":[61,73,110],"execution.":[62],"To":[63],"demonstrate":[64],"efficacy":[66],"proposed":[69],"approach,":[70,104],"ball-balancing":[72,183],"manipulability":[75],"index":[76],"maximization":[77],"was":[78],"chosen.":[79],"In":[80],"task,":[82],"7-DoF":[84],"arm":[86],"achieved":[87],"which":[94],"two":[95],"distinct":[96],"approaches":[98],"were":[99,141],"employed:":[100],"i)":[101],"human-in-the-loop":[102,156,165],"ii)":[106],"training.":[108],"The":[109],"required":[111],"bring":[115],"ball":[117,132],"center":[120],"tray":[123],"attached":[124],"its":[126],"end-effector,":[127],"starting":[128],"from":[129],"arbitrary":[130],"initial":[131],"positions":[133],"face":[136],"perturbations.":[138],"Simulation":[139],"experiments":[140],"carried":[142],"out":[143],"24":[145],"participants":[147],"where":[148],"each":[149],"participant":[150],"guided":[151],"shared":[157],"setting.":[159],"Compared":[160],"training,":[163],"approach":[167],"showed":[168],"superior":[169],"performance":[170],"terms":[172],"usage":[179],"while":[180],"exhibiting":[181],"favorable":[182],"skills.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}