{"id":"https://openalex.org/W2991256780","doi":"https://doi.org/10.1109/smc.2019.8914085","title":"Sample-Efficient Policy Learning based on Completely Behavior Cloning","display_name":"Sample-Efficient Policy Learning based on Completely Behavior Cloning","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2991256780","doi":"https://doi.org/10.1109/smc.2019.8914085","mag":"2991256780"},"language":"en","primary_location":{"id":"doi:10.1109/smc.2019.8914085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2019.8914085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)","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/A5083589564","display_name":"Qiming Zou","orcid":"https://orcid.org/0000-0001-6683-0056"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiming Zou","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398659","display_name":"Ling Wang","orcid":"https://orcid.org/0000-0001-8696-676X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345753","display_name":"Yu Li","orcid":"https://orcid.org/0000-0002-3664-6722"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Department of Management Science and Engineering, Anhui University of Technology, Maanshan, China"],"affiliations":[{"raw_affiliation_string":"Department of Management Science and Engineering, Anhui University of Technology, Maanshan, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454005","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0001-6209-6886"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083589564"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16151804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"2543","last_page":"2548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9927999973297119,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9927999973297119,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9912999868392944,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9850000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8233307600021362},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.7320208549499512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.690271258354187},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5939743518829346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5563628673553467},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5339295864105225},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.4566591680049896},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45642799139022827},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.43796271085739136},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.4361013174057007},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42320728302001953},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4136265814304352},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3658057451248169},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14958304166793823}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8233307600021362},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.7320208549499512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.690271258354187},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5939743518829346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5563628673553467},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5339295864105225},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.4566591680049896},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45642799139022827},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.43796271085739136},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.4361013174057007},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42320728302001953},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4136265814304352},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3658057451248169},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14958304166793823},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc.2019.8914085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2019.8914085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1923344279","https://openalex.org/W1931877416","https://openalex.org/W1968566045","https://openalex.org/W1973944436","https://openalex.org/W1986014385","https://openalex.org/W1993170675","https://openalex.org/W2073911623","https://openalex.org/W2104733512","https://openalex.org/W2113622443","https://openalex.org/W2121103318","https://openalex.org/W2126909264","https://openalex.org/W2142641780","https://openalex.org/W2147032798","https://openalex.org/W2151210636","https://openalex.org/W2155007355","https://openalex.org/W2257979135","https://openalex.org/W2554984891","https://openalex.org/W2726187156","https://openalex.org/W2735089625","https://openalex.org/W2736601468","https://openalex.org/W2737215407","https://openalex.org/W2750875954","https://openalex.org/W2766447205","https://openalex.org/W2783637925","https://openalex.org/W2789632256","https://openalex.org/W2804383999","https://openalex.org/W2962957031","https://openalex.org/W2963311874","https://openalex.org/W2963864421","https://openalex.org/W2964070888","https://openalex.org/W2964161785","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6640174482","https://openalex.org/W6640325754","https://openalex.org/W6675999342","https://openalex.org/W6678367057","https://openalex.org/W6680724558","https://openalex.org/W6681631837","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6729507393","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6741115023","https://openalex.org/W6741302124","https://openalex.org/W6743636021"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W2509444723","https://openalex.org/W2004958254"],"abstract_inverted_index":{"Direct":[0],"policy":[1],"search":[2],"is":[3],"one":[4],"of":[5,10,21],"the":[6,58,109],"most":[7],"important":[8],"algorithm":[9,46],"reinforcement":[11,87],"learning.":[12],"However,":[13],"learning":[14,88],"from":[15],"scratch":[16],"needs":[17],"a":[18,42,65,75],"large":[19],"amount":[20],"experience":[22],"data":[23],"and":[24,73,114,117],"can":[25,90,104],"be":[26,91],"easily":[27],"prone":[28],"to":[29,35,78,93],"poor":[30],"local":[31],"optima.":[32],"In":[33],"order":[34],"overcome":[36],"these":[37],"challenges,":[38],"this":[39,80,83,95],"paper":[40],"proposed":[41],"training-free":[43],"behavior":[44],"cloning":[45],"called":[47],"Policy":[48],"Learning":[49],"based":[50],"on":[51],"Completely":[52],"Behavior":[53],"Cloning":[54],"(PLCBC).":[55],"PLCBC":[56],"transforms":[57],"Model":[59],"Predictive":[60],"Control":[61],"(MPC)":[62],"controller":[63],"into":[64],"PieceWise":[66],"Affine":[67],"(PWA)":[68],"function":[69],"with":[70],"multi-parametric":[71],"programming,":[72],"uses":[74],"neural":[76,96],"network":[77],"express":[79],"function.":[81],"By":[82],"way,":[84],"off-the-shelf":[85],"deep":[86],"algorithms":[89],"used":[92],"fine-tune":[94],"network.":[97],"The":[98],"experiments":[99],"show":[100],"that":[101],"our":[102],"method":[103],"help":[105],"agent":[106],"learn":[107],"at":[108],"high":[110],"reward":[111],"state":[112],"region,":[113],"converge":[115],"faster":[116],"better.":[118]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}