{"id":"https://openalex.org/W51929988","doi":"https://doi.org/10.1007/3-540-56798-4_157","title":"B-Learning: A reinforcement learning algorithm, comparison with dynamic programming","display_name":"B-Learning: A reinforcement learning algorithm, comparison with dynamic programming","publication_year":1993,"publication_date":"1993-01-01","ids":{"openalex":"https://openalex.org/W51929988","doi":"https://doi.org/10.1007/3-540-56798-4_157","mag":"51929988"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-56798-4_157","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-56798-4_157","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/A5108337127","display_name":"Thibault Langlols","orcid":null},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I102516824","display_name":"Universit\u00e9 de Technologie de Compi\u00e8gne","ror":"https://ror.org/04y5kwa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I102516824"]}],"countries":["FR","PT"],"is_corresponding":true,"raw_author_name":"Thibault Langlols","raw_affiliation_strings":["INESC, Lisboa Codex, Portugal","Universit\u00e9 de Technologie de Compi\u00e8gne, Compi\u00e8gne Cedex, France"],"affiliations":[{"raw_affiliation_string":"INESC, Lisboa Codex, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"Universit\u00e9 de Technologie de Compi\u00e8gne, Compi\u00e8gne Cedex, France","institution_ids":["https://openalex.org/I102516824"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017956425","display_name":"St\u00e9phane Canu","orcid":"https://orcid.org/0000-0002-7602-4557"},"institutions":[{"id":"https://openalex.org/I102516824","display_name":"Universit\u00e9 de Technologie de Compi\u00e8gne","ror":"https://ror.org/04y5kwa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I102516824"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Canu","raw_affiliation_strings":["Universit\u00e9 de Technologie de Compi\u00e8gne, Compi\u00e8gne Cedex, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Technologie de Compi\u00e8gne, Compi\u00e8gne Cedex, France","institution_ids":["https://openalex.org/I102516824"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108337127"],"corresponding_institution_ids":["https://openalex.org/I102516824","https://openalex.org/I121345201"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03866566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9896000027656555,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9896000027656555,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9620000123977661,"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/T10320","display_name":"Neural Networks and Applications","score":0.9595999717712402,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8980246782302856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8254578709602356},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6133666038513184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5230265855789185},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46471771597862244},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42033469676971436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3677040934562683},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3577550947666168}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8980246782302856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8254578709602356},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6133666038513184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5230265855789185},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46471771597862244},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42033469676971436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3677040934562683},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3577550947666168}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/3-540-56798-4_157","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-56798-4_157","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Clean water and sanitation","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/6"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W50296447","https://openalex.org/W380254110","https://openalex.org/W2036588125","https://openalex.org/W2091565802","https://openalex.org/W2100677568","https://openalex.org/W2102295697","https://openalex.org/W2141559645"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W20361778"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
