{"id":"https://openalex.org/W2134289401","doi":null,"title":"Reinforcement learning as classification: leveraging modern classifiers","display_name":"Reinforcement learning as classification: leveraging modern classifiers","publication_year":2003,"publication_date":"2003-08-21","ids":{"openalex":"https://openalex.org/W2134289401","mag":"2134289401"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.4440","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.4440","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/~mgl/papers/PDF/icml03.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5084693234","display_name":"Michail G. Lagoudakis","orcid":"https://orcid.org/0000-0003-2803-3755","observed_orcids":["https://orcid.org/0000-0003-2803-3755"]},"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":"Michail G. Lagoudakis","raw_affiliation_strings":["Dept. of Computer Science, Duke University Durham, NC#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-2803-3755","affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Duke University Durham, NC#TAB#","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109839104","display_name":"Ronald Parr","orcid":null,"observed_orcids":[]},"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":"Ronald Parr","raw_affiliation_strings":["Dept. of Computer Science, Duke University Durham, NC#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Duke University Durham, NC#TAB#","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":5.2034,"has_fulltext":false,"cited_by_count":134,"citation_normalized_percentile":{"value":0.95504686,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"424","last_page":"431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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":0.9739999771118164},{"id":"https://openalex.org/keywords/classification","display_name":"classification","score":0.75},{"id":"https://openalex.org/keywords/classifiers","display_name":"machine learning classifiers","score":0.5640000104904175},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.5950000286102295},{"id":"https://openalex.org/keywords/monte-carlo-methods","display_name":"Monte Carlo methods","score":0.8659999966621399},{"id":"https://openalex.org/keywords/inner-loop","display_name":"inner loop","score":0.5260000228881836}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8666590452194214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7632285952568054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562536597251892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7557607293128967},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.6248756051063538},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5841208100318909},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5776886940002441},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46005532145500183},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.45740392804145813},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.4217318296432495},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.41230690479278564},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38925901055336},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29557809233665466},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07928267121315002},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.4440","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.4440","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/~mgl/papers/PDF/icml03.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.2869","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.2869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/conferences/icml2003/papers/372.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.7.474","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.474","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/~mgl/papers/icml03.ps.gz","raw_type":"text"},{"id":"mag:2134289401","doi":null,"is_oa":false,"landing_page_url":"https://users.cs.duke.edu/~parr/icml03.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1486089539","https://openalex.org/W1499408472","https://openalex.org/W1512919909","https://openalex.org/W1515851193","https://openalex.org/W1568409566","https://openalex.org/W1575592356","https://openalex.org/W1576452626","https://openalex.org/W1654728867","https://openalex.org/W1777239053","https://openalex.org/W1931792391","https://openalex.org/W2068052921","https://openalex.org/W2099833070","https://openalex.org/W2106451198","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2132096648","https://openalex.org/W2135997697","https://openalex.org/W2160067530","https://openalex.org/W2165131254"],"related_works":["https://openalex.org/W7095398013","https://openalex.org/W2104209987","https://openalex.org/W2037199950","https://openalex.org/W7097820617","https://openalex.org/W3036903532","https://openalex.org/W7099916404","https://openalex.org/W183229625","https://openalex.org/W7100599829","https://openalex.org/W1479873353","https://openalex.org/W7165549513"],"abstract_inverted_index":{"The":[0],"basic":[1],"tools":[2],"of":[3,11,20,69,76,103,111,151],"machine":[4,39,97],"learning":[5,14,35,40,65,127],"appear":[6],"in":[7,17,63,99,114,158],"the":[8,18,67,100,104,109,117,139,149,159],"inner":[9,101],"loop":[10,102],"most":[12],"reinforcement":[13,34,70,126],"algorithms,":[15],"typically":[16],"form":[19],"Monte":[21],"Carlo":[22],"methods":[23],"or":[24],"function":[25],"approximation":[26],"techniques.":[27],"To":[28],"a":[29,51,74,88,94],"large":[30],"extent,":[31],"however,":[32],"current":[33],"algorithms":[36],"draw":[37],"upon":[38],"techniques":[41],"that":[42,83,108],"are":[43],"at":[44],"least":[45],"ten":[46],"years":[47],"old":[48],"and,":[49],"with":[50,116],"few":[52],"exceptions,":[53],"very":[54],"little":[55],"has":[56],"been":[57],"done":[58],"to":[59,86,124,141],"exploit":[60],"recent":[61],"advances":[62],"classification":[64,90,143],"for":[66,172],"purposes":[68],"learning.":[71],"We":[72,106,154],"use":[73,87,110,150],"variant":[75],"approximate":[77],"policy":[78],"iteration":[79],"based":[80],"on":[81],"rollouts":[82],"allows":[84],"us":[85],"pure":[89],"learner,":[91],"such":[92],"as":[93,128],"support":[95],"vector":[96],"(SVM),":[98],"algorithm.":[105],"argue":[107],"SVMs,":[112],"particularly":[113],"combination":[115],"kernel":[118],"trick,":[119],"can":[120],"make":[121],"it":[122],"easier":[123],"apply":[125],"an":[129],"\u201coutof-the-box\u201d":[130],"technique,":[131],"without":[132],"extensive":[133],"feature":[134],"engineering.":[135],"Our":[136],"approach":[137],"opens":[138],"door":[140],"modern":[142],"methods,":[144],"but":[145],"does":[146],"not":[147],"preclude":[148],"classical":[152],"methods.":[153],"present":[155],"experimental":[156],"results":[157],"pendulum":[160],"balancing":[161],"and":[162,169],"bicycle":[163],"riding":[164],"domains":[165],"using":[166],"both":[167],"SVMs":[168],"neural":[170],"networks":[171],"classifiers.":[173],"1.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":13}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}