{"id":"https://openalex.org/W2515676083","doi":"https://doi.org/10.1177/0142331216649655","title":"Transferring knowledge from human-demonstration trajectories to reinforcement learning","display_name":"Transferring knowledge from human-demonstration trajectories to reinforcement learning","publication_year":2016,"publication_date":"2016-09-05","ids":{"openalex":"https://openalex.org/W2515676083","doi":"https://doi.org/10.1177/0142331216649655","mag":"2515676083"},"language":"en","primary_location":{"id":"doi:10.1177/0142331216649655","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0142331216649655","pdf_url":null,"source":{"id":"https://openalex.org/S24148485","display_name":"Transactions of the Institute of Measurement and Control","issn_l":"0142-3312","issn":["0142-3312","1477-0369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Institute of Measurement and Control","raw_type":"journal-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/A5054085447","display_name":"Guofang Wang","orcid":"https://orcid.org/0000-0003-2727-2607"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo-fang Wang","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048127669","display_name":"Zhou Fang","orcid":"https://orcid.org/0000-0002-5389-6694"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhou Fang","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741314","display_name":"Li Ping","orcid":"https://orcid.org/0000-0002-4933-5093"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["Department of Control Science and Engineering, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100772208","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-7095-4841"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5048127669"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.1655,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90732944,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"40","issue":"1","first_page":"94","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9966999888420105,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7724840641021729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.761833131313324},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7328618764877319},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.6044946908950806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5638453960418701},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5631834864616394},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5355417728424072},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4385654032230377},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4121738076210022},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4044017791748047},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.10501465201377869},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09658154845237732}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7724840641021729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761833131313324},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7328618764877319},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.6044946908950806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638453960418701},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5631834864616394},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5355417728424072},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4385654032230377},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4121738076210022},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4044017791748047},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.10501465201377869},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09658154845237732},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0142331216649655","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0142331216649655","pdf_url":null,"source":{"id":"https://openalex.org/S24148485","display_name":"Transactions of the Institute of Measurement and Control","issn_l":"0142-3312","issn":["0142-3312","1477-0369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Institute of Measurement and Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5244804703","display_name":"\u57fa\u4e8e\u7279\u5f81\u63d0\u53d6\u793a\u6559\u5b66\u4e60\u7684\u65cb\u7ffc\u7a7a\u4e2d\u673a\u5668\u4eba\u7279\u6280\u98de\u884c\u63a7\u5236\u7814\u7a76","funder_award_id":"61004066","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6989861307","display_name":null,"funder_award_id":"LY15F030005","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W328766226","https://openalex.org/W1494902192","https://openalex.org/W1506146479","https://openalex.org/W1514621373","https://openalex.org/W1515851193","https://openalex.org/W1563109146","https://openalex.org/W1626155273","https://openalex.org/W1680797894","https://openalex.org/W1777239053","https://openalex.org/W1949804828","https://openalex.org/W1977655452","https://openalex.org/W1980620643","https://openalex.org/W1986014385","https://openalex.org/W2004030284","https://openalex.org/W2021055657","https://openalex.org/W2031727428","https://openalex.org/W2097381042","https://openalex.org/W2097498341","https://openalex.org/W2113921460","https://openalex.org/W2114580749","https://openalex.org/W2129427976","https://openalex.org/W2137375617","https://openalex.org/W2143435603","https://openalex.org/W2165698076","https://openalex.org/W2172968643","https://openalex.org/W2262174858","https://openalex.org/W2397581010","https://openalex.org/W2552104267","https://openalex.org/W2560674852","https://openalex.org/W2608239929","https://openalex.org/W2619103847","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2076061571","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912"],"abstract_inverted_index":{"Nowadays,":[0],"transfer":[1],"learning":[2,17,167],"(TL)":[3],"has":[4],"become":[5],"a":[6,24,59,133],"crucial":[7],"technique":[8],"to":[9,88,121,131,142],"accelerate":[10,165],"the":[11,31,41,64,72,77,82,96,101,105,123,160,166,175,190,194],"slow":[12],"optimization":[13],"procedure":[14],"of":[15,30,51,71,92,104,114,126,151,163,169,197],"reinforcement":[16],"(RL)":[18],"by":[19],"re-utilizing":[20],"knowledge":[21,36,67,78,93,127,164],"acquired":[22],"in":[23,40,54,79,81,108,185,200],"previous":[25],"related":[26],"task.":[27,84],"Nevertheless,":[28],"most":[29],"current":[32,106],"relevant":[33],"research":[34],"acquires":[35],"through":[37],"RL":[38,80,170],"training":[39],"source":[42,73,109],"task,":[43],"which":[44,99],"would":[45],"be":[46],"too":[47],"time-consuming.":[48],"In":[49,187],"view":[50],"this":[52,55,188],"situation,":[53],"paper,":[56],"we":[57],"propose":[58],"novel":[60],"TL":[61],"framework":[62,199],"where":[63],"agent":[65],"extracts":[66],"from":[68,95],"human-demonstration":[69],"trajectories":[70],"task":[74],"and":[75,111,141],"reuses":[76],"target":[83],"As":[85],"for":[86,147],"what":[87],"transfer,":[89,122],"two":[90,124,161],"forms":[91,125,162],"deduced":[94],"demonstration":[97],"trajectories,":[98],"are":[100,117,128,183],"k-nearest":[102],"neighbour":[103],"state":[107],"samples":[110],"visit":[112],"frequency":[113],"homologous":[115],"states,":[116],"adopted.":[118],"For":[119],"how":[120],"respectively":[129],"used":[130,184],"recommend":[132],"preferred":[134],"action":[135],"when":[136,181],"random":[137],"exploration":[138],"is":[139,173,177],"needed":[140],"shape":[143],"an":[144],"instantaneous":[145],"reward":[146],"RL.":[148,201],"Simulation":[149],"experiments":[150],"balancing":[152],"Cart-Poles":[153],"with":[154],"different":[155],"difficulties":[156],"suggest":[157],"that":[158],"both":[159],"process":[168],"obviously.":[171],"What":[172],"more,":[174],"effect":[176],"even":[178],"more":[179],"significant":[180],"they":[182],"combination.":[186],"case,":[189],"experimental":[191],"results":[192],"manifest":[193],"positive":[195],"role":[196],"our":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}