{"id":"https://openalex.org/W2089415692","doi":"https://doi.org/10.1162/089976699300016070","title":"A Unified Analysis of Value-Function-Based Reinforcement-Learning Algorithms","display_name":"A Unified Analysis of Value-Function-Based Reinforcement-Learning Algorithms","publication_year":1999,"publication_date":"1999-11-01","ids":{"openalex":"https://openalex.org/W2089415692","doi":"https://doi.org/10.1162/089976699300016070","mag":"2089415692","pmid":"https://pubmed.ncbi.nlm.nih.gov/10578043"},"language":"en","primary_location":{"id":"doi:10.1162/089976699300016070","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976699300016070","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5069856068","display_name":"Csaba Szepesv\u00e1ri","orcid":"https://orcid.org/0000-0002-9286-2892"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Csaba Szepesv\u00e1ri","raw_affiliation_strings":["Mindmaker, Ltd., Budapest 1121, Konkoly Thege M. U. 29-33, Hungary","Mindmaker, Ltd., Budapest 1121, Konkoly Thege M. U. 29-33, Hungary#TAB#"],"affiliations":[{"raw_affiliation_string":"Mindmaker, Ltd., Budapest 1121, Konkoly Thege M. U. 29-33, Hungary","institution_ids":[]},{"raw_affiliation_string":"Mindmaker, Ltd., Budapest 1121, Konkoly Thege M. U. 29-33, Hungary#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Department of Computer Science, Duke University, Durham, NC 27708-0129, U.S.A","Department of Computer Science, Duke University, Durham, NC 27708-0129, U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Duke University, Durham, NC 27708-0129, U.S.A","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Duke University, Durham, NC 27708-0129, U.S.A.#TAB#","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069856068"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1967,"has_fulltext":false,"cited_by_count":183,"citation_normalized_percentile":{"value":0.95454932,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"11","issue":"8","first_page":"2017","last_page":"2060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.9399007558822632},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7800031900405884},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6883125305175781},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6743619441986084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6178364753723145},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6097399592399597},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.574748158454895},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5636137127876282},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4767128825187683},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4670941233634949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4557180106639862},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4537319540977478},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42701494693756104},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.41601887345314026},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35513144731521606},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.35404103994369507},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3361278176307678},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.28256356716156006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23784327507019043}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9399007558822632},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7800031900405884},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6883125305175781},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6743619441986084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6178364753723145},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6097399592399597},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.574748158454895},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5636137127876282},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4767128825187683},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4670941233634949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4557180106639862},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4537319540977478},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42701494693756104},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.41601887345314026},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35513144731521606},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.35404103994369507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3361278176307678},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28256356716156006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23784327507019043},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1162/089976699300016070","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976699300016070","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:10578043","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/10578043","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.41.9303","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.9303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.duke.edu/~mlittman/papers/nc98-gmdp.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W58217484","https://openalex.org/W134786152","https://openalex.org/W1513468570","https://openalex.org/W1515851193","https://openalex.org/W1515891729","https://openalex.org/W1542941925","https://openalex.org/W1547105496","https://openalex.org/W1548889916","https://openalex.org/W1549353711","https://openalex.org/W1557517019","https://openalex.org/W1568229137","https://openalex.org/W1576452626","https://openalex.org/W1577337550","https://openalex.org/W1603765807","https://openalex.org/W1608119595","https://openalex.org/W1610678877","https://openalex.org/W1626977535","https://openalex.org/W1994616650","https://openalex.org/W2009533501","https://openalex.org/W2021061679","https://openalex.org/W2048226872","https://openalex.org/W2082261506","https://openalex.org/W2101167844","https://openalex.org/W2101915445","https://openalex.org/W2107726111","https://openalex.org/W2113913482","https://openalex.org/W2118219918","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2125510930","https://openalex.org/W2125812768","https://openalex.org/W2147750403","https://openalex.org/W2150147323","https://openalex.org/W2150339816","https://openalex.org/W2159206500","https://openalex.org/W2165131254","https://openalex.org/W2166386822","https://openalex.org/W2170192506","https://openalex.org/W2235056388","https://openalex.org/W2314805057","https://openalex.org/W2329479259","https://openalex.org/W2531891978","https://openalex.org/W2974536256","https://openalex.org/W3011120880","https://openalex.org/W3139377883","https://openalex.org/W4233696721","https://openalex.org/W4245108548"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2101748387","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W2156021013","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"is":[2],"the":[3,15,33,64,71,92,95,99],"problem":[4],"of":[5,17,32,41,56,63,73,94,101],"generating":[6],"optimal":[7,34],"behavior":[8],"in":[9,67],"a":[10,46,53,74,85],"sequential":[11],"decision-making":[12],"environment":[13],"given":[14],"opportunity":[16],"interacting":[18],"with":[19,107],"it.":[20],"Many":[21],"algorithms":[22,43],"for":[23,111],"solving":[24],"reinforcement-learning":[25,42,59,77],"problems":[26],"work":[27],"by":[28,82,97],"computing":[29],"improved":[30],"estimates":[31],"value":[35],"function.":[36],"We":[37,90],"extend":[38],"prior":[39],"analyses":[40],"and":[44,114],"present":[45],"powerful":[47],"new":[48],"theorem":[49,65,96],"that":[50,84],"can":[51],"provide":[52],"unified":[54],"analysis":[55],"such":[57],"value-function-based":[58],"algorithms.":[60],"The":[61],"usefulness":[62],"lies":[66],"how":[68],"it":[69],"allows":[70],"convergence":[72,100],"complex":[75],"asynchronous":[76],"algorithm":[78,88],"to":[79],"be":[80],"proved":[81],"verifying":[83],"simpler":[86],"synchronous":[87],"converges.":[89],"illustrate":[91],"application":[93],"analyzing":[98],"Q-learning,":[102],"model-based":[103],"reinforcement":[104,116],"learning,":[105],"Q-learning":[106,110],"multistate":[108],"updates,":[109],"Markov":[112],"games,":[113],"risk-sensitive":[115],"learning.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}