{"id":"https://openalex.org/W1574840339","doi":"https://doi.org/10.1007/978-3-540-89722-4_8","title":"Bayesian Reward Filtering","display_name":"Bayesian Reward Filtering","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W1574840339","doi":"https://doi.org/10.1007/978-3-540-89722-4_8","mag":"1574840339"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-89722-4_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-89722-4_8","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":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/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/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"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":true,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["MCE Department, ArcelorMittal Research, Maizi\u00e8res-l\u00e8s-Metz, France","Sup\u00e9lec, IMS Research Group, Metz, France"],"affiliations":[{"raw_affiliation_string":"MCE Department, ArcelorMittal Research, Maizi\u00e8res-l\u00e8s-Metz, France","institution_ids":["https://openalex.org/I4210114269"]},{"raw_affiliation_string":"Sup\u00e9lec, IMS Research Group, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]}]},{"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":["Sup\u00e9lec, IMS Research Group, Metz, France"],"affiliations":[{"raw_affiliation_string":"Sup\u00e9lec, IMS Research Group, 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":["MCE Department, ArcelorMittal Research, Maizi\u00e8res-l\u00e8s-Metz, France"],"affiliations":[{"raw_affiliation_string":"MCE Department, ArcelorMittal Research, Maizi\u00e8res-l\u00e8s-Metz, France","institution_ids":["https://openalex.org/I4210114269"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110482875"],"corresponding_institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210114269","https://openalex.org/I4210160189"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.5018,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89759185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.81890469789505},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7649377584457397},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6135606169700623},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.606281042098999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5965536236763},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5421697497367859},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5240576267242432},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4736698269844055},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45643627643585205},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4117351174354553},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35332754254341125},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11725625395774841}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81890469789505},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7649377584457397},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6135606169700623},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.606281042098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5965536236763},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5421697497367859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5240576267242432},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4736698269844055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45643627643585205},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4117351174354553},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35332754254341125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11725625395774841},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-540-89722-4_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-89722-4_8","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:10.1.1.207.6735","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.6735","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/recherche/publis_pdf/Supelec423.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.721.9991","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.721.9991","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/EWRL_2008_MGOPGF.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00351282v1","is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00351282","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":"EWRL 2008, Jun 2008, Lille, France. pp.96-109, ⟨10.1007/978-3-540-89722-4_8⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W123280120","https://openalex.org/W1515851193","https://openalex.org/W1520710862","https://openalex.org/W1591803298","https://openalex.org/W2007655795","https://openalex.org/W2098432798","https://openalex.org/W2120772353","https://openalex.org/W2121863487","https://openalex.org/W2129670787","https://openalex.org/W2129819572","https://openalex.org/W2133733518","https://openalex.org/W2341171179"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W4306904969","https://openalex.org/W2090827041","https://openalex.org/W2094012830","https://openalex.org/W187246281"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}