{"id":"https://openalex.org/W2168335549","doi":"https://doi.org/10.1109/adprl.2011.5967385","title":"Higher order Q-Learning","display_name":"Higher order Q-Learning","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2168335549","doi":"https://doi.org/10.1109/adprl.2011.5967385","mag":"2168335549"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5112414179","display_name":"Ashley D. Edwards","orcid":"https://orcid.org/0009-0007-1129-5114"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ashley Edwards","raw_affiliation_strings":["Department of Computer Science, University of Georgia, Athens, GA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Georgia, Athens, GA, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011634099","display_name":"William M. Pottenger","orcid":null},"institutions":[{"id":"https://openalex.org/I2799411422","display_name":"Center for Discrete Mathematics and Theoretical Computer Science","ror":"https://ror.org/00k551w06","country_code":"US","type":"facility","lineage":["https://openalex.org/I102322142","https://openalex.org/I118347220","https://openalex.org/I1283103587","https://openalex.org/I1311060795","https://openalex.org/I20089843","https://openalex.org/I2799411422","https://openalex.org/I4210107353"]},{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William M. Pottenger","raw_affiliation_strings":["Department of Computer Science and DIMACS, Rutgers University, Piscataway, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and DIMACS, Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I2799411422","https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112414179"],"corresponding_institution_ids":["https://openalex.org/I165733156"],"apc_list":null,"apc_paid":null,"fwci":1.2827,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84730436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9962999820709229,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9962999820709229,"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":0.9898999929428101,"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":0.9879000186920166,"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":0.8124926090240479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7015168070793152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6794884204864502},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6501592993736267},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5827723145484924},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5784890651702881},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45381563901901245},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.441449373960495},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.43411803245544434},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.41885942220687866},{"id":"https://openalex.org/keywords/online-machine-learning","display_name":"Online machine learning","score":0.4132058918476105},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4130176901817322},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.41166117787361145},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1964987814426422},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15654399991035461},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14988937973976135},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.13729044795036316}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8124926090240479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015168070793152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6794884204864502},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6501592993736267},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5827723145484924},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5784890651702881},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45381563901901245},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.441449373960495},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43411803245544434},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.41885942220687866},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.4132058918476105},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4130176901817322},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.41166117787361145},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1964987814426422},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15654399991035461},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14988937973976135},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.13729044795036316},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2011.5967385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"},{"id":"https://openalex.org/F4320333922","display_name":"Domestic Nuclear Detection Office","ror":"https://ror.org/01y5va805"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W41690797","https://openalex.org/W1591803298","https://openalex.org/W1602633340","https://openalex.org/W1800493452","https://openalex.org/W1908728294","https://openalex.org/W2017102965","https://openalex.org/W2075342199","https://openalex.org/W2076008912","https://openalex.org/W2115477592","https://openalex.org/W2116686327","https://openalex.org/W2121250409","https://openalex.org/W2121863487","https://openalex.org/W2124965089","https://openalex.org/W2131904442","https://openalex.org/W2145076066","https://openalex.org/W2164810648","https://openalex.org/W2168788143","https://openalex.org/W2319588593","https://openalex.org/W2911283634","https://openalex.org/W2962735828","https://openalex.org/W3015720892","https://openalex.org/W3089227502","https://openalex.org/W4214717370","https://openalex.org/W4244478947","https://openalex.org/W6635327058","https://openalex.org/W6637980283","https://openalex.org/W6639917875","https://openalex.org/W6677241066","https://openalex.org/W6677432153","https://openalex.org/W6678161993","https://openalex.org/W6680642335","https://openalex.org/W6683932190","https://openalex.org/W6689723076"],"related_works":["https://openalex.org/W3148060700","https://openalex.org/W2794908468","https://openalex.org/W3210156800","https://openalex.org/W2553312496","https://openalex.org/W2042184006","https://openalex.org/W1756896031","https://openalex.org/W4319302697","https://openalex.org/W2921630034","https://openalex.org/W2531570999","https://openalex.org/W4390062853"],"abstract_inverted_index":{"Higher":[0],"order":[1],"learning":[2,7,35,41,155],"is":[3,37,49,64,67],"a":[4,38,53,69,82,90,94,114,152],"statistical":[5],"relational":[6],"framework":[8],"in":[9,42,141,151],"which":[10,99],"relationships":[11],"between":[12],"different":[13],"instances":[14],"of":[15,72,96,138,145],"the":[16,136,142],"same":[17],"class":[18],"are":[19],"leveraged":[20],"(Ganiz,":[21],"Lytkin":[22],"and":[23,120],"Pottenger,":[24],"2009).":[25],"Learning":[26],"can":[27,102],"be":[28,103],"supervised":[29],"or":[30,55,117],"unsupervised.":[31],"In":[32,77],"contrast,":[33],"reinforcement":[34,154],"(Q-Learning)":[36],"technique":[39,133],"for":[40],"an":[43],"unknown":[44],"state":[45,91],"space.":[46],"Action":[47],"selection":[48],"often":[50,68],"based":[51,123],"on":[52,124],"greedy,":[54],"epsilon":[56],"greedy":[57],"approach.":[58],"The":[59],"problem":[60,87],"with":[61],"this":[62,78,86,106,125,132],"approach":[63,84],"that":[65,88,131],"there":[66],"large":[70],"amount":[71,137],"initial":[73,143],"exploration":[74,139],"before":[75],"convergence.":[76],"article":[79],"we":[80,108],"introduce":[81],"novel":[83],"to":[85,113],"treats":[89],"space":[92],"as":[93,111],"collection":[95],"data":[97],"from":[98],"latent":[100],"information":[101],"extrapolated.":[104],"From":[105],"data,":[107],"classify":[109],"actions":[110],"leading":[112],"high":[115],"reward":[116],"low":[118],"reward,":[119],"formulate":[121],"behaviors":[122],"information.":[126],"We":[127,147],"provide":[128],"experimental":[129],"evidence":[130],"drastically":[134],"reduces":[135],"required":[140],"stages":[144],"learning.":[146],"evaluate":[148],"our":[149],"algorithm":[150],"well-known":[153],"domain,":[156],"grid-world.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}