{"id":"https://openalex.org/W2765250768","doi":"https://doi.org/10.1007/978-3-319-70139-4_42","title":"A Bayesian Posterior Updating Algorithm in Reinforcement Learning","display_name":"A Bayesian Posterior Updating Algorithm in Reinforcement Learning","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2765250768","doi":"https://doi.org/10.1007/978-3-319-70139-4_42","mag":"2765250768"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-70139-4_42","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-70139-4_42","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/A5056039500","display_name":"Fangzhou Xiong","orcid":"https://orcid.org/0000-0002-2592-4096"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fangzhou Xiong","raw_affiliation_strings":["School of Computer and Control, University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China","The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Control, University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434504","display_name":"Zhiyong Liu","orcid":"https://orcid.org/0000-0003-2148-1846"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Liu","raw_affiliation_strings":["CAS Centre for Excellence in Brain Science and Intelligence Technology (CEBSIT), Shanghai, 200031, China","Cloud Computing Center, Chinese Academy of Sciences, DongGuan, 523808, Guangdong, China","School of Computer and Control, University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China","The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"CAS Centre for Excellence in Brain Science and Intelligence Technology (CEBSIT), Shanghai, 200031, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"Cloud Computing Center, Chinese Academy of Sciences, DongGuan, 523808, Guangdong, China","institution_ids":["https://openalex.org/I4210144487"]},{"raw_affiliation_string":"School of Computer and Control, University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007963696","display_name":"Xu Yang","orcid":"https://orcid.org/0000-0003-0553-4581"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":["The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979437","display_name":"Biao Sun","orcid":"https://orcid.org/0000-0001-6677-8673"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Sun","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, 100083, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, 100083, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102147813","display_name":"Charles B. Chiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charles Chiu","raw_affiliation_strings":["School for Higher and Professional Education, Chai Wan, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"School for Higher and Professional Education, Chai Wan, Hong Kong, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026688050","display_name":"Hong Qiao","orcid":"https://orcid.org/0000-0001-6384-3687"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Qiao","raw_affiliation_strings":["CAS Centre for Excellence in Brain Science and Intelligence Technology (CEBSIT), Shanghai, 200031, China","Cloud Computing Center, Chinese Academy of Sciences, DongGuan, 523808, Guangdong, China","School of Computer and Control, University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China","The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, Beijing, 100190, China","University of Science and Technology Beijing, Beijing, 100083, China"],"affiliations":[{"raw_affiliation_string":"CAS Centre for Excellence in Brain Science and Intelligence Technology (CEBSIT), Shanghai, 200031, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"Cloud Computing Center, Chinese Academy of Sciences, DongGuan, 523808, Guangdong, China","institution_ids":["https://openalex.org/I4210144487"]},{"raw_affiliation_string":"School of Computer and Control, University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, 100083, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5056039500"],"corresponding_institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210165038"],"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":0.15739607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"418","last_page":"426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9977999925613403,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9954000115394592,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8582881689071655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8229449391365051},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6754408478736877},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.6051012277603149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5779806971549988},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5398890376091003},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5212067365646362},{"id":"https://openalex.org/keywords/prior-information","display_name":"Prior information","score":0.5041660070419312},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5033151507377625},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4673137366771698},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.46350306272506714},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3233567476272583}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8582881689071655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229449391365051},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6754408478736877},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.6051012277603149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779806971549988},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5398890376091003},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5212067365646362},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.5041660070419312},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5033151507377625},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4673137366771698},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.46350306272506714},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3233567476272583},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-70139-4_42","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-70139-4_42","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1582436621","https://openalex.org/W1591803298","https://openalex.org/W1862757251","https://openalex.org/W2071814471","https://openalex.org/W2107726111","https://openalex.org/W2108738385","https://openalex.org/W2121863487","https://openalex.org/W2122162550","https://openalex.org/W2236244207","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2032094637","https://openalex.org/W2040227828","https://openalex.org/W2902734113","https://openalex.org/W2060045818","https://openalex.org/W3091801943","https://openalex.org/W4226115828","https://openalex.org/W2131935101","https://openalex.org/W2770783108","https://openalex.org/W2407375987","https://openalex.org/W1529069387"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
