{"id":"https://openalex.org/W4405255010","doi":"https://doi.org/10.1007/978-3-031-77941-1_10","title":"Evidence on\u00a0the\u00a0Regularisation Properties of\u00a0Maximum-Entropy Reinforcement Learning","display_name":"Evidence on\u00a0the\u00a0Regularisation Properties of\u00a0Maximum-Entropy Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4405255010","doi":"https://doi.org/10.1007/978-3-031-77941-1_10"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-77941-1_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-77941-1_10","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04800896v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030882501","display_name":"R\u00e9my Hosseinkhan Boucher","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210113150","display_name":"Laboratoire Interdisciplinaire de Physique","ror":"https://ror.org/023n9q531","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210113150","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"R\u00e9my Hosseinkhan Boucher","raw_affiliation_strings":["CNRS, Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique, Orsay, France","Universit\u00e9 Paris-Saclay, Orsay, France"],"raw_orcid":"https://orcid.org/0009-0005-3382-6081","affiliations":[{"raw_affiliation_string":"CNRS, Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210113150","https://openalex.org/I4387152856"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Orsay, France","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031278952","display_name":"Onofrio Semeraro","orcid":"https://orcid.org/0000-0002-0130-0545"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210113150","display_name":"Laboratoire Interdisciplinaire de Physique","ror":"https://ror.org/023n9q531","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210113150","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Onofrio Semeraro","raw_affiliation_strings":["CNRS, Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique, Orsay, France","Universit\u00e9 Paris-Saclay, Orsay, France"],"raw_orcid":"https://orcid.org/0000-0002-0130-0545","affiliations":[{"raw_affiliation_string":"CNRS, Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210113150","https://openalex.org/I4387152856"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Orsay, France","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067613761","display_name":"Lionel Mathelin","orcid":"https://orcid.org/0000-0003-1433-4987"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210113150","display_name":"Laboratoire Interdisciplinaire de Physique","ror":"https://ror.org/023n9q531","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210113150","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lionel Mathelin","raw_affiliation_strings":["CNRS, Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique, Orsay, France","Universit\u00e9 Paris-Saclay, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS, Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210113150","https://openalex.org/I4387152856"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Orsay, France","institution_ids":["https://openalex.org/I277688954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030882501"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210113150","https://openalex.org/I4387152856"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9958999752998352,"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/T10320","display_name":"Neural Networks and Applications","score":0.9958999752998352,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11513","display_name":"stochastic dynamics and bifurcation","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6365247964859009},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.45047271251678467},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42527303099632263},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4171293377876282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.36034417152404785},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.34371575713157654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2950577139854431},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21805474162101746},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10913386940956116}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6365247964859009},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.45047271251678467},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42527303099632263},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4171293377876282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36034417152404785},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.34371575713157654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2950577139854431},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21805474162101746},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10913386940956116}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-031-77941-1_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-77941-1_10","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-04800896v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04800896","pdf_url":"https://hal.science/hal-04800896v1/document","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":"International Conference on Optimization and Learning (OLA 2024), May 2024, Dubrovnik, Croatia. &#x27E8;10.1007/978-3-031-77941-1_10&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04800896v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04800896","pdf_url":"https://hal.science/hal-04800896v1/document","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":"International Conference on Optimization and Learning (OLA 2024), May 2024, Dubrovnik, Croatia. &#x27E8;10.1007/978-3-031-77941-1_10&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3998199833","display_name":"Reinforcement learning as optimal control for fluid flows","funder_award_id":"ANR-21-CE46-0008","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405255010.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1529665736","https://openalex.org/W1583837637","https://openalex.org/W1607832978","https://openalex.org/W1868559974","https://openalex.org/W1970789124","https://openalex.org/W1990645294","https://openalex.org/W1993411524","https://openalex.org/W1993971257","https://openalex.org/W2010654234","https://openalex.org/W2069045459","https://openalex.org/W2552194003","https://openalex.org/W2754517384","https://openalex.org/W2912811302","https://openalex.org/W2985728346","https://openalex.org/W3175458185"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W2007980826","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2061531152","https://openalex.org/W3002753104"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
