{"id":"https://openalex.org/W2037199950","doi":"https://doi.org/10.1145/1102351.1102411","title":"Relating reinforcement learning performance to classification performance","display_name":"Relating reinforcement learning performance to classification performance","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2037199950","doi":"https://doi.org/10.1145/1102351.1102411","mag":"2037199950"},"language":"en","primary_location":{"id":"doi:10.1145/1102351.1102411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning  - ICML '05","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/A5005003250","display_name":"John Langford","orcid":"https://orcid.org/0000-0002-9811-3550"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Langford","raw_affiliation_strings":["TTI-Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"TTI-Chicago, Chicago, IL","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006347550","display_name":"Bianca Zadrozny","orcid":"https://orcid.org/0000-0002-7260-2057"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bianca Zadrozny","raw_affiliation_strings":["IBM T.J. Watson, Yorktown Heights, NY","IBM T.J Watson, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM T.J Watson, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005003250"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":5.937,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.95965868,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"473","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9972000122070312,"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":0.989300012588501,"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":0.7371025085449219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6978784203529358},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4402095675468445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41240859031677246},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3733065128326416},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1582508087158203},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05865234136581421}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7371025085449219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6978784203529358},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4402095675468445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41240859031677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3733065128326416},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1582508087158203},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05865234136581421}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1102351.1102411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning  - ICML '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.408.1329","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.408.1329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hunch.net/~jl/projects/reductions/RL_II/paper.pdf.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.77.1831","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.1831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2005/papers/060_Relating_LangfordZadrozny.pdf","raw_type":"text"}],"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/W95351861","https://openalex.org/W148834693","https://openalex.org/W166089536","https://openalex.org/W1515851193","https://openalex.org/W1540337045","https://openalex.org/W1564663916","https://openalex.org/W1575592356","https://openalex.org/W1576452626","https://openalex.org/W1577296257","https://openalex.org/W2121863487","https://openalex.org/W2128547596","https://openalex.org/W2134289401","https://openalex.org/W2142261479","https://openalex.org/W2161521419","https://openalex.org/W2165421048","https://openalex.org/W3023151133","https://openalex.org/W3023407077"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4306674287","https://openalex.org/W2909304650","https://openalex.org/W4319083788"],"abstract_inverted_index":{"We":[0],"prove":[1],"a":[2,12,98],"quantitative":[3],"connection":[4,22],"between":[5],"the":[6,43,49,61,64,70,84],"expected":[7],"sum":[8],"of":[9,11,30,48,51,63,69],"rewards":[10,65],"policy":[13],"and":[14,42,66],"binary":[15],"classification":[16,81],"performance":[17,68,82],"on":[18,60,83],"created":[19,71,85],"subproblems.":[20,86],"This":[21],"holds":[23],"without":[24],"any":[25],"unobservable":[26],"assumptions":[27],"(no":[28],"assumption":[29],"independence,":[31],"small":[32],"mixing":[33],"time,":[34],"fully":[35],"observable":[36],"states,":[37],"or":[38,53],"even":[39],"hidden":[40],"states)":[41],"resulting":[44],"statement":[45,56],"is":[46,57],"independent":[47],"number":[50],"states":[52],"actions.":[54],"The":[55],"critically":[58],"dependent":[59],"size":[62],"prediction":[67],"classifiers.We":[72],"also":[73],"provide":[74],"some":[75],"general":[76],"guidelines":[77],"for":[78,93,97],"obtaining":[79],"good":[80],"In":[87],"particular,":[88],"we":[89],"discuss":[90],"possible":[91],"methods":[92],"generating":[94],"training":[95],"examples":[96],"classifier":[99],"learning":[100],"algorithm.":[101]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}