{"id":"https://openalex.org/W4389409979","doi":"https://doi.org/10.1631/fitee.2300084","title":"Embedding expert demonstrations into clustering buffer for effective deep reinforcement learning","display_name":"Embedding expert demonstrations into clustering buffer for effective deep reinforcement learning","publication_year":2023,"publication_date":"2023-11-01","ids":{"openalex":"https://openalex.org/W4389409979","doi":"https://doi.org/10.1631/fitee.2300084"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2300084","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2300084","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","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/A5034243120","display_name":"Shihmin Wang","orcid":"https://orcid.org/0000-0002-7288-8323"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shihmin Wang","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7288-8323","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101276175","display_name":"Binqi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Binqi Zhao","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073046581","display_name":"Zhengfeng Zhang","orcid":"https://orcid.org/0000-0003-2025-8327"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengfeng Zhang","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028173092","display_name":"Junping Zhang","orcid":"https://orcid.org/0000-0002-5511-7463"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junping Zhang","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058626590","display_name":"Jian Pu","orcid":"https://orcid.org/0000-0002-0892-1213"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Pu","raw_affiliation_strings":["Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0892-1213","affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028173092","https://openalex.org/A5034243120","https://openalex.org/A5058626590","https://openalex.org/A5101276175"],"corresponding_institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210164150"],"apc_list":null,"apc_paid":null,"fwci":0.3173,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64451752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"24","issue":"11","first_page":"1541","last_page":"1556"},"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9864000082015991,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.965499997138977,"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":0.8363949060440063},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7723390460014343},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7047569751739502},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5237786173820496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5077563524246216},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5070860385894775},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4996814727783203},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49080023169517517},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4883274734020233},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47138744592666626},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4658445119857788},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.45549118518829346},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4467315971851349},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4455726444721222},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4413757622241974},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4354548454284668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363949060440063},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7723390460014343},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7047569751739502},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5237786173820496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5077563524246216},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5070860385894775},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4996814727783203},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49080023169517517},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4883274734020233},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47138744592666626},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4658445119857788},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.45549118518829346},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4467315971851349},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4455726444721222},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4413757622241974},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4354548454284668},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2300084","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2300084","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2049017883","https://openalex.org/W2257979135","https://openalex.org/W2788862220","https://openalex.org/W2963099939","https://openalex.org/W2982316857","https://openalex.org/W2994446013","https://openalex.org/W2998202787","https://openalex.org/W3038822267","https://openalex.org/W3096831136","https://openalex.org/W3106709020","https://openalex.org/W3110392801","https://openalex.org/W3117590843","https://openalex.org/W3137513727","https://openalex.org/W4214717370","https://openalex.org/W4293171371","https://openalex.org/W4297184265","https://openalex.org/W4307092192","https://openalex.org/W4311409157","https://openalex.org/W4319987667","https://openalex.org/W4322775461","https://openalex.org/W4324290231","https://openalex.org/W4362654154","https://openalex.org/W6640963894","https://openalex.org/W6677916085","https://openalex.org/W6814003322","https://openalex.org/W6824383132"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2365264209","https://openalex.org/W4306904969","https://openalex.org/W962203960","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2026999166","https://openalex.org/W2024136090"],"abstract_inverted_index":{"As":[0],"one":[1],"of":[2,18,34,60,93,126,150,165],"the":[3,16,40,57,61,70,88,105,108,113,127,131,156,163,171],"most":[4,23],"fundamental":[5],"topics":[6],"in":[7,69,107,112,130],"reinforcement":[8,144],"learning":[9,145],"(RL),":[10],"sample":[11,28,53],"efficiency":[12,54],"is":[13,121,179,185],"essential":[14],"to":[15,51,74,101,123],"deployment":[17],"deep":[19],"RL":[20],"algorithms.":[21],"Unlike":[22],"existing":[24],"exploration":[25,114],"methods":[26,68],"that":[27],"an":[29,46,76],"action":[30,77,109],"from":[31,104],"different":[32,138],"types":[33],"posterior":[35],"distributions,":[36],"we":[37,64,81],"focus":[38],"on":[39,136,155],"policy":[41,71],"sampling":[42,49,72],"process":[43,73],"and":[44,98,147,170],"propose":[45],"efficient":[47],"selective":[48,151],"approach":[50,120],"improve":[52],"by":[55,168,174],"modeling":[56,87],"internal":[58,89],"hierarchy":[59],"environment.":[62],"Specifically,":[63],"first":[65],"employ":[66],"clustering":[67,84],"generate":[75],"candidate":[78,110],"set.":[79],"Then":[80],"introduce":[82],"a":[83],"buffer":[85],"for":[86,181],"hierarchy,":[90],"which":[91],"consists":[92],"on-policy":[94],"data,":[95,97],"off-policy":[96],"expert":[99,132],"data":[100],"evaluate":[102],"actions":[103],"clusters":[106],"set":[111],"stage.":[115],"In":[116,153],"this":[117],"way,":[118],"our":[119,159,177],"able":[122],"take":[124],"advantage":[125],"supervision":[128],"information":[129],"demonstration":[133],"data.":[134],"Experiments":[135],"six":[137],"continuous":[139],"locomotion":[140],"environments":[141],"demonstrate":[142],"superior":[143],"performance":[146],"faster":[148],"convergence":[149,166,172],"sampling.":[152],"particular,":[154],"LGSVL":[157],"task,":[158],"method":[160],"can":[161],"reduce":[162],"number":[164],"steps":[167],"46.7%":[169],"time":[173],"28.5%.":[175],"Furthermore,":[176],"code":[178,184],"open-source":[180],"reproducibility.":[182],"The":[183],"available":[186],"at":[187],"https://github.com/Shihwin/SelectiveSampling":[188],".":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}