{"id":"https://openalex.org/W41554520","doi":"https://doi.org/10.1016/s0925-2312(00)00324-6","title":"Reinforcement Learning: An Introduction","display_name":"Reinforcement Learning: An Introduction","publication_year":2000,"publication_date":"2000-11-01","ids":{"openalex":"https://openalex.org/W41554520","doi":"https://doi.org/10.1016/s0925-2312(00)00324-6","mag":"41554520"},"language":"en","primary_location":{"id":"doi:10.1016/s0925-2312(00)00324-6","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0925-2312(00)00324-6","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"type":"article","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/A5016249965","display_name":"Jeffrey D. Johnson","orcid":"https://orcid.org/0000-0001-7651-6992"},"institutions":[{"id":"https://openalex.org/I90871651","display_name":"University of Toledo","ror":"https://ror.org/01pbdzh19","country_code":"US","type":"education","lineage":["https://openalex.org/I90871651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey D Johnson","raw_affiliation_strings":["Department of Bioengineering, The University of Toledo, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, The University of Toledo, USA","institution_ids":["https://openalex.org/I90871651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102011421","display_name":"Jinghong Li","orcid":"https://orcid.org/0009-0000-6203-8512"},"institutions":[{"id":"https://openalex.org/I90871651","display_name":"University of Toledo","ror":"https://ror.org/01pbdzh19","country_code":"US","type":"education","lineage":["https://openalex.org/I90871651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinghong Li","raw_affiliation_strings":["Department of Bioengineering, The University of Toledo, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, The University of Toledo, USA","institution_ids":["https://openalex.org/I90871651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029552362","display_name":"Zengshi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I90871651","display_name":"University of Toledo","ror":"https://ror.org/01pbdzh19","country_code":"US","type":"education","lineage":["https://openalex.org/I90871651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zengshi Chen","raw_affiliation_strings":["Department of Bioengineering, The University of Toledo, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, The University of Toledo, USA","institution_ids":["https://openalex.org/I90871651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90871651"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":11.7264,"has_fulltext":false,"cited_by_count":8698,"citation_normalized_percentile":{"value":0.98276491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"35","issue":"1-4","first_page":"205","last_page":"206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3736000061035156,"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":0.3736000061035156,"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/T10826","display_name":"Behavioral and Psychological Studies","score":0.030400000512599945,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.01720000058412552,"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":0.6880790591239929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.58819580078125},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5023272037506104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4578195810317993},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32510823011398315},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15759852528572083}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6880790591239929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.58819580078125},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5023272037506104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4578195810317993},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32510823011398315},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15759852528572083},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/s0925-2312(00)00324-6","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0925-2312(00)00324-6","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120","https://openalex.org/W3107602296","https://openalex.org/W4312192474","https://openalex.org/W4210805261"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":71},{"year":2024,"cited_by_count":1399},{"year":2023,"cited_by_count":2022},{"year":2022,"cited_by_count":1686},{"year":2021,"cited_by_count":1403},{"year":2020,"cited_by_count":1014},{"year":2019,"cited_by_count":525},{"year":2018,"cited_by_count":146},{"year":2017,"cited_by_count":52},{"year":2016,"cited_by_count":46},{"year":2015,"cited_by_count":37},{"year":2014,"cited_by_count":43},{"year":2013,"cited_by_count":24},{"year":2012,"cited_by_count":35}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}