{"id":"https://openalex.org/W2028357975","doi":"https://doi.org/10.1016/s0004-3702(98)00002-2","title":"Model-based average reward reinforcement learning","display_name":"Model-based average reward reinforcement learning","publication_year":1998,"publication_date":"1998-04-01","ids":{"openalex":"https://openalex.org/W2028357975","doi":"https://doi.org/10.1016/s0004-3702(98)00002-2","mag":"2028357975"},"language":"en","primary_location":{"id":"doi:10.1016/s0004-3702(98)00002-2","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0004-3702(98)00002-2","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-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/A5014260664","display_name":"Prasad Tadepalli","orcid":"https://orcid.org/0000-0003-2736-3912"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prasad Tadepalli","raw_affiliation_strings":["Department of Computer Science, Oregon State University, Corvallis, OR 97331, USA","Oregon State University, Corvallis"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Oregon State University, Corvallis, OR 97331, USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Oregon State University, Corvallis","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047718692","display_name":"DoKyeong Ok","orcid":null},"institutions":[{"id":"https://openalex.org/I2799667316","display_name":"Republic of Korea Army","ror":"https://ror.org/0331rkj73","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799667316"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"DoKyeong Ok","raw_affiliation_strings":["Korean Army Computer Center, NonSanSi DuMaMyeon BuNamRi, P.O.Box 29, ChungNam 320-919, South Korea","Korean Army Computer Center, ChungNam, South Korea#TAB#"],"affiliations":[{"raw_affiliation_string":"Korean Army Computer Center, NonSanSi DuMaMyeon BuNamRi, P.O.Box 29, ChungNam 320-919, South Korea","institution_ids":["https://openalex.org/I2799667316"]},{"raw_affiliation_string":"Korean Army Computer Center, ChungNam, South Korea#TAB#","institution_ids":["https://openalex.org/I2799667316"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014260664"],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":{"value":3670,"currency":"USD","value_usd":3670},"apc_paid":null,"fwci":2.197,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.8919692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"100","issue":"1-2","first_page":"177","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9958000183105469,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9958000183105469,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9923999905586243,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9858999848365784,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8606623411178589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6907452940940857},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6196632385253906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5850284695625305},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5378870368003845},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5059399008750916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45617222785949707},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4161664843559265},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4121890664100647},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3228985071182251},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2086488902568817},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08051607012748718}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8606623411178589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6907452940940857},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6196632385253906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5850284695625305},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5378870368003845},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5059399008750916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45617222785949707},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4161664843559265},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4121890664100647},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3228985071182251},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2086488902568817},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08051607012748718},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/s0004-3702(98)00002-2","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0004-3702(98)00002-2","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.2642","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.2642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.engr.oregonstate.edu/~tadepall/research/papers/arl-aij.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W65193931","https://openalex.org/W98997153","https://openalex.org/W100531594","https://openalex.org/W119094537","https://openalex.org/W131709709","https://openalex.org/W132264163","https://openalex.org/W151724613","https://openalex.org/W158125789","https://openalex.org/W165707239","https://openalex.org/W178169250","https://openalex.org/W208428353","https://openalex.org/W1491843047","https://openalex.org/W1539216098","https://openalex.org/W1549353711","https://openalex.org/W1557517019","https://openalex.org/W1565763124","https://openalex.org/W1566095837","https://openalex.org/W1583837637","https://openalex.org/W1585546214","https://openalex.org/W1597173708","https://openalex.org/W1641379095","https://openalex.org/W1650504995","https://openalex.org/W1689445748","https://openalex.org/W1851793550","https://openalex.org/W1931792391","https://openalex.org/W1979071892","https://openalex.org/W1982948368","https://openalex.org/W1994410331","https://openalex.org/W2009533501","https://openalex.org/W2020294948","https://openalex.org/W2028145673","https://openalex.org/W2040546139","https://openalex.org/W2048226872","https://openalex.org/W2098432798","https://openalex.org/W2098631313","https://openalex.org/W2100677568","https://openalex.org/W2101242010","https://openalex.org/W2101915445","https://openalex.org/W2103406407","https://openalex.org/W2103626435","https://openalex.org/W2107726111","https://openalex.org/W2117341272","https://openalex.org/W2119380668","https://openalex.org/W2119567691","https://openalex.org/W2122633037","https://openalex.org/W2141559645","https://openalex.org/W2147169507","https://openalex.org/W2157720571","https://openalex.org/W2330820318","https://openalex.org/W2608239929","https://openalex.org/W2623293810","https://openalex.org/W2914112863","https://openalex.org/W3021909058","https://openalex.org/W3041202696","https://openalex.org/W3085162807","https://openalex.org/W3134493930","https://openalex.org/W4205834900","https://openalex.org/W4244238212","https://openalex.org/W4245108548","https://openalex.org/W4301914554","https://openalex.org/W6602690695","https://openalex.org/W6604007987","https://openalex.org/W6604849862","https://openalex.org/W6605390924","https://openalex.org/W6606110872","https://openalex.org/W6606446738","https://openalex.org/W6606735428","https://openalex.org/W6608437113","https://openalex.org/W6632200469","https://openalex.org/W6633021856","https://openalex.org/W6634919779","https://openalex.org/W6636774213","https://openalex.org/W6637033378","https://openalex.org/W6639010664","https://openalex.org/W6660473291","https://openalex.org/W6675043515","https://openalex.org/W6675566566","https://openalex.org/W6677347465","https://openalex.org/W6678116171","https://openalex.org/W6683327942"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2386410636","https://openalex.org/W2025663273","https://openalex.org/W2341346307","https://openalex.org/W4225571923","https://openalex.org/W2154399718","https://openalex.org/W4387019592","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W3038962357"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}