{"id":"https://openalex.org/W2606786028","doi":"https://doi.org/10.1007/978-3-319-57351-9_1","title":"On Generalized Bellman Equations and Temporal-Difference Learning","display_name":"On Generalized Bellman Equations and Temporal-Difference Learning","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2606786028","doi":"https://doi.org/10.1007/978-3-319-57351-9_1","mag":"2606786028"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-57351-9_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-57351-9_1","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/A5014937312","display_name":"Huizhen Yu","orcid":"https://orcid.org/0000-0002-3673-0094"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Huizhen Yu","raw_affiliation_strings":["RLAI Lab, Department of Computing Science, University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"RLAI Lab, Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102303941","display_name":"Ashique Rupam Mahmood","orcid":"https://orcid.org/0000-0001-6266-162X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ashique Rupam Mahmood","raw_affiliation_strings":["RLAI Lab, Department of Computing Science, University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"RLAI Lab, Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004923102","display_name":"Richard S. Sutton","orcid":"https://orcid.org/0000-0002-3679-3415"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard S. Sutton","raw_affiliation_strings":["RLAI Lab, Department of Computing Science, University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"RLAI Lab, Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014937312"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.6955,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86793426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6530385613441467},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5886404514312744},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.574558675289154},{"id":"https://openalex.org/keywords/ergodicity","display_name":"Ergodicity","score":0.5370188355445862},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.49241673946380615},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4895714223384857},{"id":"https://openalex.org/keywords/invariant-measure","display_name":"Invariant measure","score":0.4855780005455017},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.48205670714378357},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.48094838857650757},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.47340330481529236},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.46080660820007324},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42957425117492676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2871888279914856},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.28500375151634216},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.27724477648735046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20733457803726196},{"id":"https://openalex.org/keywords/ergodic-theory","display_name":"Ergodic theory","score":0.1959250271320343},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14914864301681519},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.10518017411231995},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09624782204627991},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08535990118980408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6530385613441467},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5886404514312744},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.574558675289154},{"id":"https://openalex.org/C201779956","wikidata":"https://www.wikidata.org/wiki/Q5426803","display_name":"Ergodicity","level":2,"score":0.5370188355445862},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.49241673946380615},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4895714223384857},{"id":"https://openalex.org/C115667082","wikidata":"https://www.wikidata.org/wiki/Q4200518","display_name":"Invariant measure","level":3,"score":0.4855780005455017},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.48205670714378357},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.48094838857650757},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.47340330481529236},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.46080660820007324},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42957425117492676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2871888279914856},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.28500375151634216},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.27724477648735046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20733457803726196},{"id":"https://openalex.org/C122044880","wikidata":"https://www.wikidata.org/wiki/Q5498822","display_name":"Ergodic theory","level":2,"score":0.1959250271320343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14914864301681519},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.10518017411231995},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09624782204627991},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08535990118980408},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-57351-9_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-57351-9_1","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1499021337","https://openalex.org/W1506859583","https://openalex.org/W1514587017","https://openalex.org/W1535681442","https://openalex.org/W1547925194","https://openalex.org/W1594216983","https://openalex.org/W1594563152","https://openalex.org/W1597303641","https://openalex.org/W1600046456","https://openalex.org/W1995713768","https://openalex.org/W2002142848","https://openalex.org/W2073733021","https://openalex.org/W2087018957","https://openalex.org/W2100677568","https://openalex.org/W2107741520","https://openalex.org/W2108596215","https://openalex.org/W2119567691","https://openalex.org/W2121703796","https://openalex.org/W2139418546","https://openalex.org/W2140778663","https://openalex.org/W2141022000","https://openalex.org/W2155428489","https://openalex.org/W2160371091","https://openalex.org/W2259454103","https://openalex.org/W2334782222","https://openalex.org/W2395162158","https://openalex.org/W2411690432","https://openalex.org/W2473364827","https://openalex.org/W2560674852","https://openalex.org/W2592901955","https://openalex.org/W2605353979","https://openalex.org/W2914656440","https://openalex.org/W2953189830","https://openalex.org/W2964112145","https://openalex.org/W2964112359","https://openalex.org/W3150304496","https://openalex.org/W4300093168","https://openalex.org/W4302097244","https://openalex.org/W4302617909","https://openalex.org/W4307347247","https://openalex.org/W6601883942","https://openalex.org/W6634721143","https://openalex.org/W6803112600"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}