{"id":"https://openalex.org/W2127530277","doi":"https://doi.org/10.1007/978-3-642-10677-4_57","title":"Tracking in Reinforcement Learning","display_name":"Tracking in Reinforcement Learning","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2127530277","doi":"https://doi.org/10.1007/978-3-642-10677-4_57","mag":"2127530277"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-10677-4_57","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-10677-4_57","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":"conference-paper","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/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[{"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/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210114269","display_name":"ArcelorMittal (France)","ror":"https://ror.org/024xs2z82","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210114269","https://openalex.org/I50754188"]},{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["CORIDA project-team, INRIA Nancy - Grand Est, France","IMS Research Group, Sup\u00e9lec, Metz, France","MC Cluster, ArcelorMittal Research, Maizi\u00e8res-l\u00e8s-Metz, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CORIDA project-team, INRIA Nancy - Grand Est, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]},{"raw_affiliation_string":"IMS Research Group, Sup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"MC Cluster, ArcelorMittal Research, Maizi\u00e8res-l\u00e8s-Metz, France","institution_ids":["https://openalex.org/I4210114269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X"},"institutions":[{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["IMS Research Group, Sup\u00e9lec, Metz, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS Research Group, Sup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055682887","display_name":"Gabriel Fricout","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114269","display_name":"ArcelorMittal (France)","ror":"https://ror.org/024xs2z82","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210114269","https://openalex.org/I50754188"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gabriel Fricout","raw_affiliation_strings":["MC Cluster, ArcelorMittal Research, Maizi\u00e8res-l\u00e8s-Metz, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MC Cluster, ArcelorMittal Research, Maizi\u00e8res-l\u00e8s-Metz, France","institution_ids":["https://openalex.org/I4210114269"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.9496,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.87288075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"502","last_page":"511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9918000102043152,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9127429127693176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8179641962051392},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.7798272371292114},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6352317333221436},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5757627487182617},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5174235105514526},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5119491815567017},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.4899422526359558},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4648614823818207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.449870765209198},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4346258044242859},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4201250970363617},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3408784866333008},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32185202836990356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12982448935508728}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9127429127693176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179641962051392},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.7798272371292114},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6352317333221436},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5757627487182617},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5174235105514526},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5119491815567017},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.4899422526359558},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4648614823818207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.449870765209198},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4346258044242859},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4201250970363617},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3408784866333008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32185202836990356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12982448935508728},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-642-10677-4_57","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-10677-4_57","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:10.1.1.207.8166","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.8166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.metz.supelec.fr/metz/personnel/geist_mat/pdfs/Supelec539.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.703.3367","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.703.3367","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/ICONIP_2009_MGOP.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00439316v1","is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00439316","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"16th International Conference on Neural Information Processing - ICONIP 2009, Dec 2009, Bangkok, Thailand. pp.502-511, ⟨10.1007/978-3-642-10677-4_57⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W34092776","https://openalex.org/W41554520","https://openalex.org/W1520710862","https://openalex.org/W1574840339","https://openalex.org/W1597303641","https://openalex.org/W1646707810","https://openalex.org/W2007655795","https://openalex.org/W2072931156","https://openalex.org/W2100379997","https://openalex.org/W2104753538","https://openalex.org/W2105934661","https://openalex.org/W2114537044","https://openalex.org/W2121863487","https://openalex.org/W2123487311","https://openalex.org/W2130801532","https://openalex.org/W2132351269","https://openalex.org/W2136602922","https://openalex.org/W2141562047","https://openalex.org/W2156974606","https://openalex.org/W2163533082","https://openalex.org/W2172968643","https://openalex.org/W4242606736","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2386410636","https://openalex.org/W2341346307","https://openalex.org/W2025663273","https://openalex.org/W2154399718","https://openalex.org/W3099153698","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W3038962357"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}