乐胖代购免代理版

{"id":"https://openalex.org/W2347074400","doi":"https://doi.org/10.1109/tnnls.2016.2543000","title":"Bridging the Gap Between Imitation Learning and Inverse Reinforcement Learning","display_name":"Bridging the Gap Between Imitation Learning and Inverse Reinforcement Learning","publication_year":2016,"publication_date":"2016-05-04","ids":{"openalex":"https://openalex.org/W2347074400","doi":"https://doi.org/10.1109/tnnls.2016.2543000","mag":"2347074400","pmid":"https://pubmed.ncbi.nlm.nih.gov/27164607"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2016.2543000","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01629654/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051968502","display_name":"Bilal Piot","orcid":"https://orcid.org/0000-0002-6456-7183"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"Bilal Piot","raw_affiliation_strings":["DeepMind [London] (United Kingdom)","SEQUEL - Sequential Learning (Centre Inria de l'Universit\u00e9 de Lille ,170 Av. de Bretagne, 59000 Lille - France)"],"affiliations":[{"raw_affiliation_string":"DeepMind [London] (United Kingdom)","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"SEQUEL - Sequential Learning (Centre Inria de l'Universit\u00e9 de Lille ,170 Av. de Bretagne, 59000 Lille - France)","institution_ids":["https://openalex.org/I2279609970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145544","display_name":"Laboratoire Interdisciplinaire des Environnements Continentaux","ror":"https://ror.org/05je79696","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210107625","https://openalex.org/I4210145544","https://openalex.org/I4210148025","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["CentraleSup\u00e9lec (3, rue Joliot Curie,\r\nPlateau de Moulon,\r\n91192 GIF-SUR-YVETTE Cedex - France)","LIEC - Laboratoire Interdisciplinaire des Environnements Continentaux (Site Charmois : 15 Avenue du Charmois, F-54500 VANDOEUVRE-LES-NANCY ; \r\nSite Aiguillettes : Facult\u00e9 des Sciences et Technologies, F-54506 VANDOEUVRE-LES-NANCY ; \r\nSite Bridoux : Campus Bridoux - Rue du G\u00e9n\u00e9ral Delestraint, F-57070 METZ ; \r\nSite Thionville : IUT de Thionville-Yutz - Espace Cormontaigne, F-57970 THIONVILLE-YUTZ - France)"],"affiliations":[{"raw_affiliation_string":"LIEC - Laboratoire Interdisciplinaire des Environnements Continentaux (Site Charmois : 15 Avenue du Charmois, F-54500 VANDOEUVRE-LES-NANCY ; \r\nSite Aiguillettes : Facult\u00e9 des Sciences et Technologies, F-54506 VANDOEUVRE-LES-NANCY ; \r\nSite Bridoux : Campus Bridoux - Rue du G\u00e9n\u00e9ral Delestraint, F-57070 METZ ; \r\nSite Thionville : IUT de Thionville-Yutz - Espace Cormontaigne, F-57970 THIONVILLE-YUTZ - France)","institution_ids":["https://openalex.org/I4210145544"]},{"raw_affiliation_string":"CentraleSup\u00e9lec (3, rue Joliot Curie,\r\nPlateau de Moulon,\r\n91192 GIF-SUR-YVETTE Cedex - France)","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X"},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["DeepMind [London] (United Kingdom)","SEQUEL - Sequential Learning (Centre Inria de l'Universit\u00e9 de Lille ,170 Av. de Bretagne, 59000 Lille - France)"],"affiliations":[{"raw_affiliation_string":"SEQUEL - Sequential Learning (Centre Inria de l'Universit\u00e9 de Lille ,170 Av. de Bretagne, 59000 Lille - France)","institution_ids":["https://openalex.org/I2279609970"]},{"raw_affiliation_string":"DeepMind [London] (United Kingdom)","institution_ids":["https://openalex.org/I4210090411"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.887,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":61,"citation_normalized_percentile":{"value":0.89961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"28","issue":"8","first_page":"1814","last_page":"1826"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9996,"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":0.9996,"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":0.9962,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9782,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/operator","display_name":"Operator (biology)","score":0.4234529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.68225855},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.55872625},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.52544874},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.50303215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4871773},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.43305755},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4234529},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.17407504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15397209},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2016.2543000","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.science/hal-01629654","pdf_url":"https://hal.science/hal-01629654/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01629654/file/TNNLS_2016_BPMGOP.pdf","pdf_url":"https://hal.archives-ouvertes.fr/hal-01629654/file/TNNLS_2016_BPMGOP.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.science/hal-01629654/file/TNNLS_2016_BPMGOP.pdf","pdf_url":"https://hal.science/hal-01629654/file/TNNLS_2016_BPMGOP.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01629654/document","pdf_url":"https://hal.archives-ouvertes.fr/hal-01629654/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27164607","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://hal.science/hal-01629654","pdf_url":"https://hal.science/hal-01629654/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.76,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":48,"referenced_works":["https://openalex.org/W102873864","https://openalex.org/W1521625446","https://openalex.org/W1540685400","https://openalex.org/W1591992921","https://openalex.org/W1748932423","https://openalex.org/W1799240622","https://openalex.org/W1931877416","https://openalex.org/W1986014385","https://openalex.org/W1994123361","https://openalex.org/W1994480928","https://openalex.org/W1999874108","https://openalex.org/W2031571562","https://openalex.org/W2056132907","https://openalex.org/W2061562262","https://openalex.org/W2097826433","https://openalex.org/W2098432798","https://openalex.org/W2098774185","https://openalex.org/W2100401322","https://openalex.org/W2103235543","https://openalex.org/W2110652811","https://openalex.org/W2113023245","https://openalex.org/W2113475501","https://openalex.org/W2116774898","https://openalex.org/W2119567691","https://openalex.org/W2119785746","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2128812357","https://openalex.org/W2133068870","https://openalex.org/W2142641780","https://openalex.org/W2148051740","https://openalex.org/W2148112459","https://openalex.org/W2148603752","https://openalex.org/W2167224731","https://openalex.org/W2169498096","https://openalex.org/W2270835334","https://openalex.org/W2334782222","https://openalex.org/W2396161314","https://openalex.org/W2474718355","https://openalex.org/W2544683879","https://openalex.org/W2568646110","https://openalex.org/W2586680856","https://openalex.org/W2962957031","https://openalex.org/W33732390","https://openalex.org/W4206567137","https://openalex.org/W4214717370","https://openalex.org/W4236078638","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W3168977894","https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2341346307","https://openalex.org/W2145363145","https://openalex.org/W1985560493","https://openalex.org/W1626977535"],"abstract_inverted_index":{"Learning":[0],"from":[1,71,142,229,260],"demonstrations":[2,21,74],"is":[3,28,49,65,102,109,133,225],"a":[4,12,16,50,68,110,136,159,197,207,226],"paradigm":[5,51],"by":[6,19,23],"which":[7,143,230,240],"an":[8,24,171],"apprentice":[9,63],"agent":[10,64],"learns":[11],"control":[13],"policy":[14],"for":[15,244],"dynamic":[17],"environment":[18],"observing":[20],"delivered":[22],"expert":[25,73,79,91],"agent.":[26],"It":[27],"usually":[29],"implemented":[30],"as":[31,123],"either":[32],"imitation":[33],"learning":[34,39],"(IL)":[35],"or":[36],"inverse":[37,177],"reinforcement":[38],"(IRL)":[40],"in":[41,87,94,158,165,292],"the":[42,45,54,59,62,72,78,82,90,95,128,166,176,192,201,204,209,215,242,245,252,256,261,267,271,279,284],"literature.":[43],"On":[44,81],"one":[46],"hand,":[47,84],"IRL":[48,154,212,234,257,286],"relying":[52],"on":[53],"Markov":[55],"decision":[56],"processes,":[57],"where":[58],"goal":[60],"of":[61,113,130,185,217],"to":[66,97,105,125,134,249,270],"find":[67],"reward":[69],"function":[70],"that":[75,151,161,168,195,278],"could":[76],"explain":[77],"behavior.":[80],"other":[83],"IL":[85,152,202,210,232,246,288],"consists":[86],"directly":[88],"generalizing":[89],"strategy,":[92],"observed":[93],"demonstrations,":[96],"unvisited":[98],"states":[99],"(and":[100],"it":[101,224],"therefore":[103],"close":[104],"classification,":[106],"when":[107],"there":[108,169],"finite":[111],"set":[112],"possible":[114],"decisions).":[115],"While":[116],"these":[117,140],"two":[118],"visions":[119],"are":[120,163,220,264],"often":[121],"considered":[122],"opposite":[124],"each":[126],"other,":[127],"purpose":[129],"this":[131],"paper":[132],"exhibit":[135],"formal":[137],"link":[138,199],"between":[139,181,200],"approaches":[141],"new":[144],"algorithms":[145,235,258,268,281],"can":[146,155,236],"be":[147,156,237],"derived.":[148],"We":[149],"show":[150],"and":[153,203,211,233,239,287,290],"redefined":[157],"way":[160,243],"they":[162],"equivalent,":[164],"sense":[167],"exists":[170],"explicit":[172],"bijective":[173],"operator":[174],"(namely,":[175],"optimal":[178],"Bellman":[179],"operator)":[180],"their":[182],"respective":[183],"spaces":[184],"solutions.":[186,295],"To":[187],"do":[188],"so,":[189],"we":[190],"introduce":[191],"set-policy":[193,262],"framework":[194,228,263],"creates":[196],"clear":[198],"IRL.":[205],"As":[206],"result,":[208],"solutions":[213],"making":[214],"best":[216],"both":[218,283],"worlds":[219],"obtained.":[221],"In":[222],"addition,":[223],"unifying":[227],"existing":[231],"derived":[238,259],"opens":[241],"methods":[247],"able":[248],"deal":[250],"with":[251,266],"environment's":[253],"dynamics.":[254],"Finally,":[255],"compared":[265],"belonging":[269],"more":[272,293],"common":[273],"trajectory-matching":[274],"family.":[275],"Experiments":[276],"demonstrate":[277],"set-policy-based":[280],"outperform":[282],"standard":[285],"ones":[289],"result":[291],"robust":[294]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2347074400","counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8}],"updated_date":"2024-12-20T03:48:14.258060","created_date":"2016-06-24"}