{"id":"https://openalex.org/W7125962649","doi":"https://doi.org/10.1109/access.2026.3658497","title":"Closer to Human: Hybrid Training of VR Agents Beyond Robotic Motion","display_name":"Closer to Human: Hybrid Training of VR Agents Beyond Robotic Motion","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125962649","doi":"https://doi.org/10.1109/access.2026.3658497"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3658497","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3658497","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3658497","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124068882","display_name":"Mohamad Sobhi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134562","display_name":"HESAM Universit\u00e9","ror":"https://ror.org/042949r55","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamad Sobhi","raw_affiliation_strings":["LISPEN, Arts et Métiers Institute of Technology, Chalon-Sur-Saône, France"],"raw_orcid":"https://orcid.org/0000-0003-1031-6829","affiliations":[{"raw_affiliation_string":"LISPEN, Arts et Métiers Institute of Technology, Chalon-Sur-Saône, France","institution_ids":["https://openalex.org/I4210134562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075263388","display_name":"Mahdiyeh Sadat Moosavi","orcid":"https://orcid.org/0009-0008-2030-2950"},"institutions":[{"id":"https://openalex.org/I4210134562","display_name":"HESAM Universit\u00e9","ror":"https://ror.org/042949r55","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mahdiyeh Sadat Moosavi","raw_affiliation_strings":["LISPEN, Arts et Métiers Institute of Technology, Chalon-Sur-Saône, France"],"raw_orcid":"https://orcid.org/0009-0008-2030-2950","affiliations":[{"raw_affiliation_string":"LISPEN, Arts et Métiers Institute of Technology, Chalon-Sur-Saône, France","institution_ids":["https://openalex.org/I4210134562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083984732","display_name":"Christophe Guillet","orcid":"https://orcid.org/0000-0001-8104-4600"},"institutions":[{"id":"https://openalex.org/I4210134562","display_name":"HESAM Universit\u00e9","ror":"https://ror.org/042949r55","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christophe Guillet","raw_affiliation_strings":["LISPEN, Arts et Métiers Institute of Technology, Chalon-Sur-Saône, France"],"raw_orcid":"https://orcid.org/0000-0001-8104-4600","affiliations":[{"raw_affiliation_string":"LISPEN, Arts et Métiers Institute of Technology, Chalon-Sur-Saône, France","institution_ids":["https://openalex.org/I4210134562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124061644","display_name":"Frederic Merienne","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134562","display_name":"HESAM Universit\u00e9","ror":"https://ror.org/042949r55","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric M\u00e9rienne","raw_affiliation_strings":["LISPEN, Arts et Métiers Institute of Technology, Chalon-Sur-Saône, France"],"raw_orcid":"https://orcid.org/0000-0003-4466-4776","affiliations":[{"raw_affiliation_string":"LISPEN, Arts et Métiers Institute of Technology, Chalon-Sur-Saône, France","institution_ids":["https://openalex.org/I4210134562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079893426","display_name":"Mohammad Mehdi Ebadzadeh","orcid":"https://orcid.org/0000-0001-6466-5229"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad Mehdi Ebadzadeh","raw_affiliation_strings":["Amirkabir University of Technology, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0001-6466-5229","affiliations":[{"raw_affiliation_string":"Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08119512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"18940","last_page":"18951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.3409000039100647,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.3409000039100647,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.12999999523162842,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.12269999831914902,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6134999990463257},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5727999806404114},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.48829999566078186},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4790000021457672},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.47679999470710754},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.46880000829696655},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.39820000529289246},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.38370001316070557},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.3666999936103821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486000061035156},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6134999990463257},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5473999977111816},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5170000195503235},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3666999936103821},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3666999936103821},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.35260000824928284},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.29499998688697815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C150303390","wikidata":"https://www.wikidata.org/wiki/Q1983852","display_name":"Virtual actor","level":3,"score":0.26170000433921814}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3658497","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3658497","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5b40c00a76d042c895f5354766be2f4f","is_oa":false,"landing_page_url":"https://doaj.org/article/5b40c00a76d042c895f5354766be2f4f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 18940-18951 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3658497","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3658497","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5025055408477783}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W170732776","https://openalex.org/W1987474762","https://openalex.org/W2107726111","https://openalex.org/W2123339228","https://openalex.org/W2141707954","https://openalex.org/W2162130878","https://openalex.org/W2547922594","https://openalex.org/W2562184125","https://openalex.org/W2963669336","https://openalex.org/W3088501792","https://openalex.org/W3172917672","https://openalex.org/W3205396610","https://openalex.org/W3207037710","https://openalex.org/W3215521197","https://openalex.org/W4200025042","https://openalex.org/W4220664097","https://openalex.org/W4310849374","https://openalex.org/W4361281660","https://openalex.org/W4377942440","https://openalex.org/W4381570152","https://openalex.org/W4385788468","https://openalex.org/W4390575687","https://openalex.org/W4392456038","https://openalex.org/W4392595364","https://openalex.org/W4396833393","https://openalex.org/W4399119592","https://openalex.org/W4399926700","https://openalex.org/W4401170035","https://openalex.org/W4402602243","https://openalex.org/W4407476753","https://openalex.org/W4409326453","https://openalex.org/W4409763459","https://openalex.org/W4410087662","https://openalex.org/W4410611668","https://openalex.org/W4411171604","https://openalex.org/W4411202769","https://openalex.org/W4411534782","https://openalex.org/W4412017442","https://openalex.org/W4412736354","https://openalex.org/W4413147695","https://openalex.org/W4414419111"],"related_works":[],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2],"virtual":[3],"reality":[4],"(VR)":[5],"agents":[6,53,131,156,178],"is":[7],"not":[8],"solely":[9],"defined":[10],"by":[11],"task":[12,115,161],"completion;":[13],"adaptability":[14],"and":[15,32,48,58,80,119,125,129,148,163,173,213,227],"the":[16,177,209],"ability":[17],"to":[18,51,127,167],"move":[19],"beyond":[20,60],"repetitive,":[21],"robotic":[22],"behavior":[23,182],"are":[24],"equally":[25],"critical":[26],"for":[27,68,76,86,186,207,220],"embodiment,":[28],"social":[29],"interaction,":[30],"rehabilitation,":[31,225],"training.":[33,201],"To":[34],"address":[35],"this":[36,101],"challenge,":[37],"we":[38],"propose":[39],"a":[40,104,111,117,205],"hybrid":[41,199],"training":[42],"methodology":[43,210],"that":[44,54,92,154,190],"integrates":[45],"imitation":[46],"learning":[47,50],"reinforcement":[49],"develop":[52],"both":[55],"master":[56],"tasks":[57],"generalize":[59],"demonstrations.":[61],"Our":[62],"framework":[63,102],"combines":[64],"Behavioral":[65],"Cloning":[66],"(BC)":[67],"rapid":[69],"policy":[70],"initialization,":[71],"Proximal":[72],"Policy":[73],"Optimization":[74],"(PPO)":[75],"stable":[77,158],"reinforcement-driven":[78],"learning,":[79,216],"Generative":[81],"Adversarial":[82],"Imitation":[83],"Learning":[84],"(GAIL)":[85],"imitation-based":[87],"rewards,":[88],"resulting":[89],"in":[90,103,224],"policies":[91],"converge":[93],"efficiently":[94],"while":[95],"avoiding":[96],"repetitive":[97],"imitation.":[98],"We":[99],"implemented":[100],"Unity-based":[105],"VR":[106,222],"environment,":[107],"where":[108],"participants":[109],"performed":[110],"single-joint":[112],"cube":[113],"pick-and-place":[114],"using":[116],"headset":[118],"controller.":[120],"Human":[121],"demonstrations":[122,169],"were":[123],"collected":[124],"used":[126],"train":[128],"evaluate":[130],"against":[132],"multiple":[133],"motion":[134,164,215],"metrics,":[135],"including":[136],"Dynamic":[137],"Time":[138],"Warping":[139],"(DTW),":[140],"Fr\u00e9chet":[141],"distance,":[142],"minimum":[143],"jerk":[144],"cost,":[145],"Fitts\u2019s":[146],"law,":[147],"curvature\u2013velocity":[149],"coupling.":[150],"Experimental":[151],"results":[152],"showed":[153],"hybrid-trained":[155],"achieved":[157],"convergence,":[159],"consistent":[160],"mastery,":[162],"trajectories":[165],"comparable":[166],"human":[168],"across":[170],"temporal,":[171],"spatial,":[172],"smoothness":[174],"dimensions.":[175],"Notably,":[176],"exhibited":[179],"adaptive,":[180],"non-repetitive":[181],"without":[183],"explicitly":[184],"optimizing":[185],"biomechanical":[187],"fidelity,":[188],"suggesting":[189],"human-like":[191],"variability":[192],"can":[193],"emerge":[194],"naturally":[195],"from":[196],"our":[197],"customized":[198],"IL+RL":[200],"These":[202],"findings":[203],"provide":[204],"foundation":[206],"scaling":[208],"toward":[211],"multi-joint":[212],"full-body":[214],"with":[217],"promising":[218],"implications":[219],"future":[221],"applications":[223],"training,":[226],"embodied":[228],"interaction.":[229]},"counts_by_year":[],"updated_date":"2026-02-11T14:41:00.668223","created_date":"2026-01-29T00:00:00"}