{"id":"https://openalex.org/W1721038333","doi":"https://doi.org/10.1007/978-3-642-29946-9_12","title":"\u21131-Penalized Projected Bellman Residual","display_name":"\u21131-Penalized Projected Bellman Residual","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1721038333","doi":"https://doi.org/10.1007/978-3-642-29946-9_12","mag":"1721038333"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-29946-9_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-29946-9_12","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://inria.hal.science/hal-00644507","any_repository_has_fulltext":true},"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"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Matthieu Geist","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/A5032281855","display_name":"Bruno Scherrer","orcid":"https://orcid.org/0000-0001-6097-4489"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bruno Scherrer","raw_affiliation_strings":["INRIA, MAIA Project-Team, Nancy, France"],"affiliations":[{"raw_affiliation_string":"INRIA, MAIA Project-Team, Nancy, France","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110482875"],"corresponding_institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.7996,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.942589,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T11236","display_name":"Control Systems and Identification","score":0.9943000078201294,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9919000267982483,"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/regularization","display_name":"Regularization (linguistics)","score":0.8008207082748413},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7731282114982605},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.673674464225769},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6549962162971497},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.580486536026001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5308811664581299},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.51596599817276},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4615374505519867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3867824673652649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38670963048934937},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37999024987220764}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.8008207082748413},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7731282114982605},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.673674464225769},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6549962162971497},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.580486536026001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5308811664581299},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.51596599817276},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4615374505519867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3867824673652649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38670963048934937},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37999024987220764}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-642-29946-9_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-29946-9_12","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:10.1.1.220.6770","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.220.6770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/64/45/07/PDF/gs_ewrl_l1_cr.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00644507v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00644507","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 Wrokshop on Reinforcement Learning (EWRL 11), Sep 2011, Athens, Greece","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00644507v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00644507","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 Wrokshop on Reinforcement Learning (EWRL 11), Sep 2011, Athens, Greece","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1460549585","https://openalex.org/W1511421254","https://openalex.org/W1515851193","https://openalex.org/W1537100889","https://openalex.org/W1576452626","https://openalex.org/W1597303641","https://openalex.org/W1730555343","https://openalex.org/W1986931325","https://openalex.org/W2020925091","https://openalex.org/W2028599032","https://openalex.org/W2046513829","https://openalex.org/W2057682568","https://openalex.org/W2063978378","https://openalex.org/W2072931156","https://openalex.org/W2073384958","https://openalex.org/W2075268401","https://openalex.org/W2075490785","https://openalex.org/W2104753538","https://openalex.org/W2108430473","https://openalex.org/W2108596215","https://openalex.org/W2110486110","https://openalex.org/W2112264645","https://openalex.org/W2123979492","https://openalex.org/W2132351269","https://openalex.org/W2135046866","https://openalex.org/W2158738729","https://openalex.org/W2158883409","https://openalex.org/W2170233819","https://openalex.org/W2522381472","https://openalex.org/W3105120000","https://openalex.org/W4211221179"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2386410636","https://openalex.org/W2341346307","https://openalex.org/W2025663273","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W3099153698","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W3038962357"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
