{"id":"https://openalex.org/W2786530308","doi":"https://doi.org/10.3233/jifs-17052","title":"Shaping in reinforcement learning by knowledge transferred from human-demonstrations of a simple similar task","display_name":"Shaping in reinforcement learning by knowledge transferred from human-demonstrations of a simple similar task","publication_year":2018,"publication_date":"2018-01-12","ids":{"openalex":"https://openalex.org/W2786530308","doi":"https://doi.org/10.3233/jifs-17052","mag":"2786530308"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-17052","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-17052","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology","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":["Zhejiang University","School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, 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":["Zhejiang University","School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741315","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-8515-7773"},"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":["Zhejiang University","School of Control Science and Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Control Science and Engineering, Zhejiang University, Hangzhou, 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":0.1638,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5600715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"34","issue":"1","first_page":"711","last_page":"720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9901000261306763,"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/computer-science","display_name":"Computer science","score":0.7539008855819702},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7032852172851562},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6598192453384399},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6363990306854248},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5906261205673218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5251336097717285},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5090345740318298},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.508239209651947},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4530186653137207},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4505680799484253},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4189945161342621},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4176703989505768},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.4154853820800781},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3306303024291992},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21152910590171814},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12110880017280579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539008855819702},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7032852172851562},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6598192453384399},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6363990306854248},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5906261205673218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5251336097717285},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5090345740318298},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.508239209651947},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4530186653137207},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4505680799484253},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4189945161342621},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4176703989505768},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.4154853820800781},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3306303024291992},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21152910590171814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12110880017280579},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-17052","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-17052","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4300000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1453801241","https://openalex.org/W1506146479","https://openalex.org/W1563109146","https://openalex.org/W1777239053","https://openalex.org/W1845972764","https://openalex.org/W1977655452","https://openalex.org/W1980620643","https://openalex.org/W1986014385","https://openalex.org/W2004030284","https://openalex.org/W2031727428","https://openalex.org/W2046376809","https://openalex.org/W2069300867","https://openalex.org/W2071302132","https://openalex.org/W2097381042","https://openalex.org/W2097498341","https://openalex.org/W2109910161","https://openalex.org/W2113921460","https://openalex.org/W2129427976","https://openalex.org/W2137375617","https://openalex.org/W2165698076","https://openalex.org/W2172968643","https://openalex.org/W2257979135","https://openalex.org/W2262174858","https://openalex.org/W2397581010","https://openalex.org/W2515676083","https://openalex.org/W3103379718"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W2038908348","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Reusing":[0],"knowledge":[1,26,39,51,65],"obtained":[2],"in":[3,43,53,66,76,123,139,156],"other":[4],"related":[5],"but":[6],"different":[7,96,129,146,176,179],"tasks":[8,97],"to":[9,49,73,80,162,210],"accelerate":[10],"the":[11,29,77,91,112,115,119,126,132,136,143,153,164,184,201,211],"learning":[12,16],"procedure":[13],"of":[14,32,55,64,85,95,128,135,145,166,171,213],"reinforcement":[15],"(RL)":[17],"has":[18],"attracted":[19],"more":[20,22,110,206,219],"and":[21,24,83,118,142,178,208],"attention":[23],"expert":[25],"transfer":[27,50],"is":[28],"root":[30],"cause":[31],"positive":[33],"effect.":[34],"Nevertheless,":[35],"compared":[36],"with":[37,90,152,175],"acquiring":[38],"by":[40,102],"RL":[41,82],"training":[42],"source":[44,56,124,140,157,220],"tasks,":[45],"this":[46],"paper":[47],"proposes":[48],"contained":[52],"human-demonstrations":[54],"tasks.":[57],"Based":[58],"on":[59],"this,":[60],"three":[61,185],"specific":[62],"forms":[63],"total":[67],"are":[68,87,159,205],"mined":[69],"from":[70],"demonstration":[71],"trajectories":[72],"be":[74,100,198],"reused":[75],"target":[78,116,137,154],"task":[79],"shape":[81],"all":[84,183],"them":[86],"closely":[88],"associated":[89],"similarity":[92,113,151],"between":[93,114],"states":[94],"which":[98],"can":[99,196],"measured":[101],"Euclidean":[103],"distance":[104],"via":[105],"human-supplied":[106],"inter-task":[107],"mappings.":[108],"In":[109,193],"detail,":[111],"state":[117,122,138,155],"most":[120],"similar":[121],"samples,":[125],"proportion":[127,144],"actions":[130,147],"among":[131],"k":[133],"-NN":[134],"samples":[141,158],"under":[148],"a":[149],"constant":[150],"respectively":[160],"selected":[161],"initialize":[163],"value":[165],"state-action":[167],"function.":[168],"Simulation":[169],"experiments":[170],"mountain":[172],"car":[173],"problems":[174],"difficulties":[177],"dimensions":[180],"suggest":[181],"that":[182,200],"shaping":[186],"methods":[187,204],"could":[188],"obviously":[189],"speed":[190],"up":[191],"RL.":[192],"comparison,":[194],"it":[195,217],"also":[197],"found":[199],"two":[202],"latter":[203],"robust":[207],"efficient":[209],"quality":[212],"human":[214],"demonstrations":[215],"as":[216],"takes":[218],"samples\u2019":[221],"information":[222],"into":[223],"consideration.":[224]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}