{"id":"https://openalex.org/W4362650413","doi":"https://doi.org/10.1007/978-981-19-7784-8","title":"Reinforcement Learning for Sequential Decision and Optimal Control","display_name":"Reinforcement Learning for Sequential Decision and Optimal Control","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4362650413","doi":"https://doi.org/10.1007/978-981-19-7784-8"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-19-7784-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-19-7784-8","pdf_url":"https://link.springer.com/content/pdf/bfm:978-981-19-7784-8/1?pdf=chapter%20toc","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"book"},"type":"book","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/bfm:978-981-19-7784-8/1?pdf=chapter%20toc","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100747108"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":58.2842,"has_fulltext":true,"cited_by_count":188,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.055799998342990875,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.055799998342990875,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.728878915309906},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5530791282653809},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5258902907371521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.403491348028183},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.36258935928344727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3382493853569031},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12048369646072388}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.728878915309906},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5530791282653809},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5258902907371521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.403491348028183},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36258935928344727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382493853569031},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12048369646072388}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-981-19-7784-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-19-7784-8","pdf_url":"https://link.springer.com/content/pdf/bfm:978-981-19-7784-8/1?pdf=chapter%20toc","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"book"},{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-035687751","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/978-981-19-7784-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-981-19-7784-8","pdf_url":"https://link.springer.com/content/pdf/bfm:978-981-19-7784-8/1?pdf=chapter%20toc","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"book"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362650413.pdf","grobid_xml":"https://content.openalex.org/works/W4362650413.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656"],"abstract_inverted_index":{"This":[0],"book":[1],"provides":[2],"a":[3],"systematic":[4],"and":[5,15],"thorough":[6],"introduction":[7],"to":[8],"reinforcement":[9],"learning,":[10],"from":[11],"both":[12],"artificial":[13],"intelligence":[14],"feedback":[16],"control":[17],"perspectives.":[18]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":84},{"year":2024,"cited_by_count":68},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-04T09:04:59.091469","created_date":"2025-10-10T00:00:00"}