{"id":"https://openalex.org/W2098146604","doi":"https://doi.org/10.1109/ijcnn.2004.1380847","title":"Reinforcement learning in the real world","display_name":"Reinforcement learning in the real world","publication_year":2005,"publication_date":"2005-01-31","ids":{"openalex":"https://openalex.org/W2098146604","doi":"https://doi.org/10.1109/ijcnn.2004.1380847","mag":"2098146604"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2004.1380847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","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/A5089808068","display_name":"Andrew G. Barto","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"A.G. Barto","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, Canada","Dept. of Comput. Sci., Massachusetts Univ., Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, Canada","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Massachusetts Univ., Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089808068"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.4388,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.74008329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"3","issue":null,"first_page":"1661","last_page":"1661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.09549999982118607,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.09549999982118607,"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":0.9231449961662292},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.7071243524551392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6485641598701477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5413051247596741},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4964056611061096},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48276272416114807},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.472381591796875},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.45878416299819946},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.4384167492389679},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13220524787902832}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9231449961662292},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7071243524551392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485641598701477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5413051247596741},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4964056611061096},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48276272416114807},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.472381591796875},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.45878416299819946},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.4384167492389679},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13220524787902832},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2004.1380847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W2391666574","https://openalex.org/W2061783822","https://openalex.org/W2352650970","https://openalex.org/W1493952344","https://openalex.org/W8539471","https://openalex.org/W1544514152","https://openalex.org/W3203256658"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"Reinforcement":[4],"learning":[5,19,104,117,166,184],"refers":[6],"to":[7,17,45,121,130,149,174],"improving":[8],"performance":[9],"through":[10],"trial-and-error":[11],"experience.":[12],"Although,":[13],"modern":[14,115],"computational":[15],"approaches":[16],"reinforcement":[18,103,116,165,183],"were":[20],"inspired":[21],"by":[22,156],"animal":[23],"learning,":[24,128],"they":[25,89,96],"have":[26,83],"now":[27],"branched":[28],"out":[29,158],"in":[30,40,75,77,85,187],"a":[31,159],"very":[32,99],"several":[33,134],"different":[34,100],"directions.":[35],"Some":[36],"researchers":[37],"are":[38,51,58],"interested":[39],"finding":[41],"high-quality":[42],"approximate":[43],"solutions":[44],"large-scale":[46],"stochastic":[47],"planning":[48],"problems":[49],"that":[50,169,172],"important":[52],"for":[53],"industry":[54],"and":[55,88,105,118,129,138],"government.":[56],"Others":[57],"pursuing":[59],"the":[60,92,111,142,162,170],"goal":[61],"of":[62,114,126,141,161,164,182],"building":[63],"intelligent,":[64],"resourceful":[65],"autonomous":[66],"agents":[67],"that,":[68],"like":[69],"animals,":[70],"can":[71],"succeed":[72],"while":[73],"acting":[74],"real-time":[76],"complex":[78,152],"environments.":[79],"While":[80],"these":[81],"goals":[82],"much":[84],"common":[86],"-":[87,95],"both":[90],"involve":[91],"real":[93],"world":[94],"represent":[97],"two":[98],"perspectives":[101],"on":[102,179],"related":[106],"methods.":[107],"After":[108],"first":[109],"reviewing":[110],"major":[112],"elements":[113],"its":[119],"relationship":[120],"optimal":[122],"control,":[123],"other":[124],"types":[125],"machine":[127],"neuroscience,":[131],"I":[132,154],"present":[133],"striking":[135],"example":[136],"applications":[137],"describe":[139],"some":[140],"latest":[143],"research":[144],"directed":[145],"toward":[146],"scaling":[147],"up":[148],"ever":[150],"more":[151],"problems.":[153],"conclude":[155],"laying":[157],"view":[160],"future":[163],"research,":[167],"emphasizing":[168],"issues":[171],"need":[173],"be":[175],"addressed":[176],"depend":[177],"strongly":[178],"which":[180],"type":[181],"one":[185],"has":[186],"mind.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}