{"id":"https://openalex.org/W4413918347","doi":"https://doi.org/10.1109/icra55743.2025.11127396","title":"Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach","display_name":"Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413918347","doi":"https://doi.org/10.1109/icra55743.2025.11127396"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.vu.nl/en/publications/3a1c6ba4-7e8d-41c4-b56d-b544cff37dbc","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076858389","display_name":"Muhan Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Muhan Hou","raw_affiliation_strings":["Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071518251","display_name":"Koen V. Hindriks","orcid":"https://orcid.org/0000-0002-5707-5236"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Koen Hindriks","raw_affiliation_strings":["Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074492402","display_name":"A. E. Eiben","orcid":"https://orcid.org/0000-0002-3106-4213"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"A.E. Eiben","raw_affiliation_strings":["Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023767001","display_name":"Kim Baraka","orcid":"https://orcid.org/0000-0003-4381-4234"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kim Baraka","raw_affiliation_strings":["Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076858389"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12633254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7392","last_page":"7398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9308000206947327,"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":0.9308000206947327,"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":0.7754329442977905},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6946219801902771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6811027526855469},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.50641930103302},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4759276211261749},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.47123822569847107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4004610776901245},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.27201607823371887}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7754329442977905},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6946219801902771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6811027526855469},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.50641930103302},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4759276211261749},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47123822569847107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4004610776901245},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.27201607823371887}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra55743.2025.11127396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:openaire/3a1c6ba4-7e8d-41c4-b56d-b544cff37dbc","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/3a1c6ba4-7e8d-41c4-b56d-b544cff37dbc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hou, M, Hindriks, K, Eiben, A E & Baraka, K 2025, Robot Policy Transfer with Online Demonstrations : An Active Reinforcement Learning Approach. in C Ott, H Admoni, S Behnke, S Bogdan, A Bolopion, Y Choi, F Ficuciello, N Gans, C Gosselin, K Harada, E Kayacan, H J Kim, S Leutenegger, Z Liu, P Maiolino, L Marques, T Matsubara, A Mavromatti, M Minor, J O'Kane, H W Park, H-W Park, I Rekleitis, F Renda, E Ricci, L D Riek, L Sabattini, S Shen, Y Sun, P-B Wieber, K Yamane & J Yu (eds), 2025 IEEE International Conference on Robotics and Automation (ICRA) : [Proceedings]. Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 7392-7398, 2025 IEEE International Conference on Robotics and Automation, ICRA 2025, Atlanta, United States, 19/05/25. https://doi.org/10.1109/ICRA55743.2025.11127396","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.vu.nl:publications/3a1c6ba4-7e8d-41c4-b56d-b544cff37dbc","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/3a1c6ba4-7e8d-41c4-b56d-b544cff37dbc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hou, M, Hindriks, K, Eiben, A E & Baraka, K 2025, Robot Policy Transfer with Online Demonstrations : An Active Reinforcement Learning Approach. in C Ott, H Admoni, S Behnke, S Bogdan, A Bolopion, Y Choi, F Ficuciello, N Gans, C Gosselin, K Harada, E Kayacan, H J Kim, S Leutenegger, Z Liu, P Maiolino, L Marques, T Matsubara, A Mavromatti, M Minor, J O'Kane, H W Park, H-W Park, I Rekleitis, F Renda, E Ricci, L D Riek, L Sabattini, S Shen, Y Sun, P-B Wieber, K Yamane & J Yu (eds), 2025 IEEE International Conference on Robotics and Automation (ICRA) : [Proceedings]. Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 7392-7398, 2025 IEEE International Conference on Robotics and Automation, ICRA 2025, Atlanta, United States, 19/05/25. https://doi.org/10.1109/ICRA55743.2025.11127396","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:research.vu.nl:openaire/3a1c6ba4-7e8d-41c4-b56d-b544cff37dbc","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/3a1c6ba4-7e8d-41c4-b56d-b544cff37dbc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hou, M, Hindriks, K, Eiben, A E & Baraka, K 2025, Robot Policy Transfer with Online Demonstrations : An Active Reinforcement Learning Approach. in C Ott, H Admoni, S Behnke, S Bogdan, A Bolopion, Y Choi, F Ficuciello, N Gans, C Gosselin, K Harada, E Kayacan, H J Kim, S Leutenegger, Z Liu, P Maiolino, L Marques, T Matsubara, A Mavromatti, M Minor, J O'Kane, H W Park, H-W Park, I Rekleitis, F Renda, E Ricci, L D Riek, L Sabattini, S Shen, Y Sun, P-B Wieber, K Yamane & J Yu (eds), 2025 IEEE International Conference on Robotics and Automation (ICRA) : [Proceedings]. Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 7392-7398, 2025 IEEE International Conference on Robotics and Automation, ICRA 2025, Atlanta, United States, 19/05/25. https://doi.org/10.1109/ICRA55743.2025.11127396","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2110064869","https://openalex.org/W2515676083","https://openalex.org/W2799745602","https://openalex.org/W2903242674","https://openalex.org/W2914626659","https://openalex.org/W2966994213","https://openalex.org/W3001507548","https://openalex.org/W3003852841","https://openalex.org/W3197594072","https://openalex.org/W3202542428","https://openalex.org/W4206491580","https://openalex.org/W4316662143","https://openalex.org/W4387071728","https://openalex.org/W4388623329","https://openalex.org/W4388623949","https://openalex.org/W4402545715","https://openalex.org/W4404553824","https://openalex.org/W4410893076"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W4220829754","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"Transfer":[0,123],"Learning":[1,33],"(TL)":[2],"is":[3],"a":[4,116,149,178,182,186,251],"powerful":[5],"tool":[6],"that":[7,88,134,195],"enables":[8],"robots":[9],"to":[10,29,51,98,111,176,185,212],"transfer":[11,57,118,133,163,177,240],"learned":[12],"policies":[13],"across":[14,164],"different":[15,189],"environments,":[16],"tasks,":[17],"or":[18],"embodiments.":[19],"To":[20],"further":[21],"facilitate":[22],"this":[23],"process,":[24],"efforts":[25],"have":[26],"been":[27],"made":[28],"combine":[30],"it":[31],"with":[32,102,124,173,217,225],"from":[34,62,181],"Demonstrations":[35],"(LfD)":[36],"for":[37,131,143],"more":[38],"flexible":[39],"and":[40,72,96,139,170,208,220],"efficient":[41],"policy":[42,56,77,100,117,132,162,180,237,248],"transfer.":[43,78],"However,":[44],"these":[45,109],"approaches":[46],"are":[47],"almost":[48],"exclusively":[49],"limited":[50,150],"offline":[52,218],"demonstrations":[53,90,114,147,219],"collected":[54],"before":[55],"starts,":[58],"which":[59],"may":[60],"suffer":[61],"the":[63,74,83,137,174,235,243,247],"intrinsic":[64],"issue":[65],"of":[66,76,141,204,234],"covariance":[67,94],"shift":[68,95],"brought":[69],"by":[70],"LfD":[71,129,215,223],"harm":[73],"performance":[75,101],"Meanwhile,":[79],"extensive":[80],"work":[81,107],"in":[82,157,202,242],"learning-from-scratch":[84],"setting":[85],"has":[86],"shown":[87],"online":[89,113,144,226],"can":[91,135],"effectively":[92],"alleviate":[93],"lead":[97],"better":[99],"improved":[103],"sample":[104,209],"efficiency.":[105],"This":[106],"combines":[108],"insights":[110],"introduce":[112],"into":[115],"setting.":[119],"We":[120,153],"present":[121],"Policy":[122],"Online":[125],"Demonstrations,":[126],"an":[127],"active":[128,222],"algorithm":[130],"optimize":[136],"timing":[138],"content":[140],"queries":[142],"episodic":[145],"expert":[146],"under":[148],"demonstration":[151],"budget.":[152],"evaluate":[154],"our":[155,196],"method":[156,197,224],"eight":[158],"robotic":[159,171],"scenarios,":[160],"involving":[161],"diverse":[165],"environment":[166],"characteristics,":[167],"task":[168,184],"objectives,":[169],"embodiments,":[172],"aim":[175],"trained":[179],"source":[183],"related":[187],"but":[188],"target":[190],"task.":[191],"The":[192],"results":[193],"show":[194],"significantly":[198],"outperforms":[199],"all":[200],"baselines":[201],"terms":[203],"average":[205],"success":[206],"rate":[207],"efficiency,":[210],"compared":[211],"two":[213],"canonical":[214],"methods":[216],"one":[221],"demonstrations.":[227],"Additionally,":[228],"we":[229],"conduct":[230],"preliminary":[231],"sim-to-real":[232],"tests":[233],"transferred":[236],"on":[238,250],"three":[239],"scenarios":[241],"real-world":[244],"environment,":[245],"demonstrating":[246],"effectiveness":[249],"real":[252],"robot":[253],"manipulator.":[254]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}