{"id":"https://openalex.org/W106792269","doi":"https://doi.org/10.1007/978-3-662-44851-9_35","title":"Boosted Bellman Residual Minimization Handling Expert Demonstrations","display_name":"Boosted Bellman Residual Minimization Handling Expert Demonstrations","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W106792269","doi":"https://doi.org/10.1007/978-3-662-44851-9_35","mag":"106792269"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-662-44851-9_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-662-44851-9_35","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://centralesupelec.hal.science/hal-01060953","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/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4407990293","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Bilal Piot","raw_affiliation_strings":["Sup\u00e9lec, IMS-MaLIS Research group, France","UMI 2958 (GeorgiaTech-CNRS), France"],"affiliations":[{"raw_affiliation_string":"Sup\u00e9lec, IMS-MaLIS Research group, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"UMI 2958 (GeorgiaTech-CNRS), France","institution_ids":["https://openalex.org/I4210089931","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4407990293","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["Sup\u00e9lec, IMS-MaLIS Research group, France","UMI 2958 (GeorgiaTech-CNRS), France"],"affiliations":[{"raw_affiliation_string":"Sup\u00e9lec, IMS-MaLIS Research group, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"UMI 2958 (GeorgiaTech-CNRS), France","institution_ids":["https://openalex.org/I4210089931","https://openalex.org/I1294671590"]}]},{"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/I174424907","display_name":"Laboratoire d'Informatique Fondamentale de Lille","ror":"https://ror.org/05rhg0h08","country_code":"FR","type":"facility","lineage":["https://openalex.org/I174424907"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["University Lille 1, LIFL (UMR 8022 CNRS/Lille 1) - SequeL team, Lille, France"],"affiliations":[{"raw_affiliation_string":"University Lille 1, LIFL (UMR 8022 CNRS/Lille 1) - SequeL team, Lille, France","institution_ids":["https://openalex.org/I174424907","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051968502"],"corresponding_institution_ids":["https://openalex.org/I102475099","https://openalex.org/I1294671590","https://openalex.org/I4210089931","https://openalex.org/I4210160189"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.8095,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.84831812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"549","last_page":"564"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9937999844551086,"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"}},{"id":"https://openalex.org/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/markov-decision-process","display_name":"Markov decision process","score":0.7534363269805908},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.612692654132843},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5839148759841919},{"id":"https://openalex.org/keywords/reproducing-kernel-hilbert-space","display_name":"Reproducing kernel Hilbert space","score":0.562113344669342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5580407381057739},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5305051803588867},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.523292601108551},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.45637190341949463},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44313958287239075},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.43194615840911865},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.41279712319374084},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3288806676864624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3268486261367798},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2917259633541107},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2874631881713867},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.11248871684074402}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7534363269805908},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.612692654132843},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5839148759841919},{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.562113344669342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5580407381057739},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5305051803588867},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.523292601108551},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.45637190341949463},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44313958287239075},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.43194615840911865},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.41279712319374084},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3288806676864624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3268486261367798},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2917259633541107},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2874631881713867},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.11248871684074402},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-662-44851-9_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-662-44851-9_35","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.653.2907","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.653.2907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal-supelec.archives-ouvertes.fr/hal-01060953/document/","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.5001","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.5001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cristal.univ-lille.fr/%7Epietquin/pdf/ECML_2014_OPMGBP.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01060953v1","is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-01060953","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"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":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Conference, ECML PKDD 2014, Sep 2014, Nancy, France. pp.549-564, ⟨10.1007/978-3-662-44851-9_35⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01060953v1","is_oa":true,"landing_page_url":"https://centralesupelec.hal.science/hal-01060953","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"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":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Conference, ECML PKDD 2014, Sep 2014, Nancy, France. pp.549-564, ⟨10.1007/978-3-662-44851-9_35⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W33732390","https://openalex.org/W1516618490","https://openalex.org/W1594031697","https://openalex.org/W1854866626","https://openalex.org/W1898511152","https://openalex.org/W1986280275","https://openalex.org/W1994123361","https://openalex.org/W1999874108","https://openalex.org/W2000985550","https://openalex.org/W2012547817","https://openalex.org/W2015263936","https://openalex.org/W2072931156","https://openalex.org/W2075672181","https://openalex.org/W2098432798","https://openalex.org/W2100401322","https://openalex.org/W2102847492","https://openalex.org/W2104753538","https://openalex.org/W2119567691","https://openalex.org/W2124331852","https://openalex.org/W2128812357","https://openalex.org/W2133552775","https://openalex.org/W2148051740","https://openalex.org/W2169498096","https://openalex.org/W2334782222","https://openalex.org/W2544683879","https://openalex.org/W2949361666","https://openalex.org/W2953101296","https://openalex.org/W2962957031","https://openalex.org/W4206567137","https://openalex.org/W4211092921","https://openalex.org/W4235073738","https://openalex.org/W4236078638","https://openalex.org/W4254884888","https://openalex.org/W4285719527","https://openalex.org/W6631189298"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W4389475841","https://openalex.org/W2952594763","https://openalex.org/W4285537323","https://openalex.org/W2903299703","https://openalex.org/W4385342861","https://openalex.org/W4281791088","https://openalex.org/W2117282672","https://openalex.org/W1574958246"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}