{"id":"https://openalex.org/W3207342878","doi":"https://doi.org/10.1109/icra48506.2021.9561842","title":"Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation","display_name":"Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3207342878","doi":"https://doi.org/10.1109/icra48506.2021.9561842","mag":"3207342878"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5100389418","display_name":"Yao Yao","orcid":"https://orcid.org/0000-0001-9887-4301"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yao Yao","raw_affiliation_strings":["Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China","TBSI, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"TBSI, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375307","display_name":"Xiao Li","orcid":"https://orcid.org/0000-0002-7992-3873"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xiao","raw_affiliation_strings":["Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China","TBSI, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"TBSI, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110809917","display_name":"Zhicheng An","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng An","raw_affiliation_strings":["Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China","TBSI, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"TBSI, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072408261","display_name":"Wanpeng Zhang","orcid":"https://orcid.org/0000-0001-5351-3449"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanpeng Zhang","raw_affiliation_strings":["Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China","TBSI, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"TBSI, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101186016","display_name":"Dijun Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dijun Luo","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100389418"],"corresponding_institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.6316,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.86795499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4202","last_page":"4208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9972000122070312,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9891999959945679,"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":0.8636583089828491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7542303800582886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7430662512779236},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6534932851791382},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6373282074928284},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6282461881637573},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5228890776634216},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.5177634954452515},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5085691213607788},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.4640120267868042},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45950835943222046}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8636583089828491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7542303800582886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430662512779236},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6534932851791382},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6373282074928284},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6282461881637573},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5228890776634216},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5177634954452515},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5085691213607788},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.4640120267868042},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45950835943222046},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W172298727","https://openalex.org/W192920577","https://openalex.org/W779494576","https://openalex.org/W1826234144","https://openalex.org/W1845972764","https://openalex.org/W1980035368","https://openalex.org/W1988526405","https://openalex.org/W2076337359","https://openalex.org/W2101524054","https://openalex.org/W2102928860","https://openalex.org/W2121863487","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2168405694","https://openalex.org/W2416041116","https://openalex.org/W2417786368","https://openalex.org/W2553347458","https://openalex.org/W2781726626","https://openalex.org/W2785389871","https://openalex.org/W2789824229","https://openalex.org/W2810754397","https://openalex.org/W2885550588","https://openalex.org/W2898585858","https://openalex.org/W2902907165","https://openalex.org/W2904453761","https://openalex.org/W2920362155","https://openalex.org/W2947861305","https://openalex.org/W2951595529","https://openalex.org/W2953772919","https://openalex.org/W2962802563","https://openalex.org/W2963092423","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2963680188","https://openalex.org/W2963704132","https://openalex.org/W2963820385","https://openalex.org/W2963960193","https://openalex.org/W2970277495","https://openalex.org/W2979533262","https://openalex.org/W2982316857","https://openalex.org/W2990747716","https://openalex.org/W2997896361","https://openalex.org/W3013618273","https://openalex.org/W3025660841","https://openalex.org/W3034956653","https://openalex.org/W3035146082","https://openalex.org/W3041764008","https://openalex.org/W3081263239","https://openalex.org/W3172115140","https://openalex.org/W4287779179","https://openalex.org/W4288319859","https://openalex.org/W4297789758","https://openalex.org/W4298206671","https://openalex.org/W6622487243","https://openalex.org/W6638836233","https://openalex.org/W6675458235","https://openalex.org/W6680657880","https://openalex.org/W6689664320","https://openalex.org/W6716474083","https://openalex.org/W6730127522","https://openalex.org/W6747473740","https://openalex.org/W6748519856","https://openalex.org/W6748817170","https://openalex.org/W6751494529","https://openalex.org/W6753264383","https://openalex.org/W6753925943","https://openalex.org/W6756192075","https://openalex.org/W6756840741","https://openalex.org/W6757469721","https://openalex.org/W6760405395","https://openalex.org/W6762863188","https://openalex.org/W6763282038","https://openalex.org/W6764053384","https://openalex.org/W6768884620","https://openalex.org/W6775522024","https://openalex.org/W6778000925","https://openalex.org/W6779491353","https://openalex.org/W6780559895","https://openalex.org/W6780571964"],"related_works":["https://openalex.org/W2064636555","https://openalex.org/W2585503716","https://openalex.org/W1939982668","https://openalex.org/W2105014086","https://openalex.org/W2076090200","https://openalex.org/W3025682415","https://openalex.org/W2081173909","https://openalex.org/W4389009659","https://openalex.org/W198251434","https://openalex.org/W4312933423"],"abstract_inverted_index":{"Model-based":[0],"deep":[1],"reinforcement":[2],"learning":[3],"has":[4],"achieved":[5],"success":[6],"in":[7,135,158],"various":[8],"domains":[9],"that":[10,60,78,100,147],"require":[11],"high":[12],"sample":[13,159],"efficiencies,":[14],"such":[15,26],"as":[16,27],"Go":[17],"and":[18,44,65,93,105,153],"robotics.":[19],"However,":[20],"there":[21],"are":[22,116],"some":[23],"remaining":[24],"issues,":[25,53],"planning":[28],"efficient":[29],"explorations":[30],"to":[31,118,123],"learn":[32],"more":[33,45],"accurate":[34],"dynamic":[35],"models,":[36,43],"evaluating":[37],"the":[38,41,75,80,97],"uncertainty":[39,126],"of":[40,48,62,90],"learned":[42],"rational":[46],"utilization":[47],"models.":[49],"To":[50],"mitigate":[51],"these":[52],"we":[54],"present":[55],"MEEE,":[56],"a":[57,88],"model-ensemble":[58],"method":[59],"consists":[61],"optimistic":[63],"exploration":[64],"weighted":[66],"exploitation.":[67],"During":[68,111],"exploration,":[69],"unlike":[70],"prior":[71],"methods":[72],"directly":[73],"selecting":[74],"optimal":[76,98],"action":[77,91,99],"maximizes":[79],"expected":[81,103],"accumulative":[82],"return,":[83],"our":[84,148],"agent":[85,136],"first":[86],"generates":[87],"set":[89],"candidates":[92],"then":[94],"seeks":[95],"out":[96],"takes":[101],"both":[102],"return":[104],"future":[106],"observation":[107],"novelty":[108],"into":[109],"account.":[110],"exploitation,":[112],"different":[113],"discounted":[114],"weights":[115],"assigned":[117],"imagined":[119],"transition":[120],"tuples":[121],"according":[122],"their":[124],"model":[125,131],"respectively,":[127],"which":[128],"will":[129],"prevent":[130],"predictive":[132],"error":[133],"propagation":[134],"training.":[137],"Experiments":[138],"on":[139],"several":[140],"challenging":[141],"continuous":[142],"control":[143],"benchmark":[144],"tasks":[145],"demonstrated":[146],"approach":[149],"outperforms":[150],"other":[151],"model-free":[152],"model-based":[154],"state-of-the-art":[155],"methods,":[156],"especially":[157],"complexity.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}