{"id":"https://openalex.org/W2100752967","doi":"https://doi.org/10.1109/adprl.2009.4927542","title":"A theoretical and empirical analysis of Expected Sarsa","display_name":"A theoretical and empirical analysis of Expected Sarsa","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2100752967","doi":"https://doi.org/10.1109/adprl.2009.4927542","mag":"2100752967"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-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/A5049195732","display_name":"Harm van Seijen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094335","display_name":"Ministry of Defence","ror":"https://ror.org/0079deh61","country_code":"NL","type":"government","lineage":["https://openalex.org/I4210094335","https://openalex.org/I4210140876"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Harm van Seijen","raw_affiliation_strings":["Integrated Systems group, TNO Defence, Safety and Security, The Hague, Netherlands","Integrated Systems group, TNO Defense, Safety and Security, The Hague, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Integrated Systems group, TNO Defence, Safety and Security, The Hague, Netherlands","institution_ids":["https://openalex.org/I4210094335"]},{"raw_affiliation_string":"Integrated Systems group, TNO Defense, Safety and Security, The Hague, The Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033135596","display_name":"Hado van Hasselt","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hado van Hasselt","raw_affiliation_strings":["Intelligent Systems Group, University of Utrecht, Utrecht, Netherlands","Intelligent Systems Group, Utrecht University, The Netherlands#TAB#"],"affiliations":[{"raw_affiliation_string":"Intelligent Systems Group, University of Utrecht, Utrecht, Netherlands","institution_ids":[]},{"raw_affiliation_string":"Intelligent Systems Group, Utrecht University, The Netherlands#TAB#","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["Intelligent Autonomous Systems Group, University of Amsterdam, Amsterdam, Netherlands","Intelligent Autonomous Systems Group, University of Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Group, University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Intelligent Autonomous Systems Group, University of Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Wiering","raw_affiliation_strings":["Department of Artificial Intelligence, University of Groningam, Groningen, Netherlands","Dept. of Artificial Intelligence, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, University of Groningam, Groningen, Netherlands","institution_ids":["https://openalex.org/I169381384"]},{"raw_affiliation_string":"Dept. of Artificial Intelligence, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049195732"],"corresponding_institution_ids":["https://openalex.org/I4210094335"],"apc_list":null,"apc_paid":null,"fwci":1.8065,"has_fulltext":false,"cited_by_count":198,"citation_normalized_percentile":{"value":0.87702736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9891999959945679,"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/T11182","display_name":"Auction Theory and Applications","score":0.9799000024795532,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7495574355125427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6557477712631226},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6129451990127563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5020267963409424},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4929628372192383},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4677213728427887},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44855010509490967},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4119938313961029},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34529951214790344},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32438233494758606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26073306798934937}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7495574355125427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557477712631226},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6129451990127563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5020267963409424},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4929628372192383},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4677213728427887},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44855010509490967},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4119938313961029},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34529951214790344},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32438233494758606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26073306798934937},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/adprl.2009.4927542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/ec90bef6-3ce8-4bbe-bdfc-7a4c8ccefc69","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/a-theoretical-and-empirical-analysis-of-expected-sarsa(ec90bef6-3ce8-4bbe-bdfc-7a4c8ccefc69).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"van Seijen, H, van Hasselt, H, Whiteson, S & Wiering, M 2009, A theoretical and empirical analysis of Expected Sarsa. in Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning. pp. 177-184, 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE ADPRL 2009), Nashville, TN, USA, 30/03/09. https://doi.org/10.1109/ADPRL.2009.4927542","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.rug.nl:publications/45f8062a-203c-4d2f-821e-8d32e8ffaa5d","is_oa":false,"landing_page_url":"https://research.rug.nl/en/publications/45f8062a-203c-4d2f-821e-8d32e8ffaa5d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"van Seijen, H, van Hasselt, H, Whiteson, S & Wiering, M 2009, A Theoretical and Empirical Analysis of Expected Sarsa. in Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning : ADPRL.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.216.4144","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.216.4144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.science.uva.nl/research/isla/pub/vanSeijen09adprl.pdf","raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:publications/ec90bef6-3ce8-4bbe-bdfc-7a4c8ccefc69","is_oa":false,"landing_page_url":"http://dare.uva.nl/personal/pure/en/publications/a-theoretical-and-empirical-analysis-of-expected-sarsa(ec90bef6-3ce8-4bbe-bdfc-7a4c8ccefc69).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"van Seijen, H, van Hasselt, H, Whiteson, S & Wiering, M 2009, A theoretical and empirical analysis of Expected Sarsa. in Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning. pp. 177-184, 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE ADPRL 2009), Nashville, TN, USA, 30/03/09. https://doi.org/10.1109/ADPRL.2009.4927542","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1547105496","https://openalex.org/W1646707810","https://openalex.org/W2076337359","https://openalex.org/W2100677568","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2125074935","https://openalex.org/W2150339816","https://openalex.org/W2341171179","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4244566287","https://openalex.org/W6678114464","https://openalex.org/W6678545291"],"related_works":["https://openalex.org/W2341346307","https://openalex.org/W3096874164","https://openalex.org/W2154399718","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W2145363145","https://openalex.org/W3148138296","https://openalex.org/W2152445738","https://openalex.org/W4388937744"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,11,61],"theoretical":[4],"and":[5,47,78,89,98],"empirical":[6],"analysis":[7],"of":[8,64],"Expected":[9,24,54,69,84,101],"Sarsa,":[10,14],"variation":[12],"on":[13],"the":[15,31,73],"classic":[16],"on-policy":[17],"temporal-difference":[18],"method":[19],"for":[20,43],"model-free":[21],"reinforcement":[22],"learning.":[23,50],"Sarsa":[25,70,77,85,88,102],"exploits":[26],"knowledge":[27],"about":[28,82],"stochasticity":[29],"in":[30,92],"behavior":[32],"policy":[33],"to":[34],"perform":[35],"updates":[36,56],"with":[37],"lower":[38],"variance.":[39],"Doing":[40],"so":[41],"allows":[42],"higher":[44],"learning":[45,62],"rates":[46],"thus":[48],"faster":[49],"In":[51],"deterministic":[52],"environments,":[53],"Sarsas":[55],"have":[57],"zero":[58],"variance,":[59],"enabling":[60],"rate":[63],"1.":[65],"We":[66],"prove":[67],"that":[68,100],"converges":[71],"under":[72],"same":[74],"conditions":[75],"as":[76],"formulate":[79],"specific":[80],"hypotheses":[81,97],"when":[83],"will":[86],"outperform":[87],"Q-learning.":[90],"Experiments":[91],"multiple":[93],"domains":[94],"confirm":[95],"these":[96,107],"demonstrate":[99],"has":[103],"significant":[104],"advantages":[105],"over":[106],"more":[108],"commonly":[109],"used":[110],"methods.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}