{"id":"https://openalex.org/W2096258902","doi":"https://doi.org/10.1145/1390156.1390194","title":"Active reinforcement learning","display_name":"Active reinforcement learning","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2096258902","doi":"https://doi.org/10.1145/1390156.1390194","mag":"2096258902"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","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/A5040720036","display_name":"Arkady Epshteyn","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arkady Epshteyn","raw_affiliation_strings":["Google Inc., Pittsburgh, PA","Google, Inc., Pittsburgh, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Pittsburgh, PA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc., Pittsburgh, PA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070930882","display_name":"Adam P. Vogel","orcid":"https://orcid.org/0000-0002-3505-2631"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Vogel","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043767069","display_name":"Gerald DeJong","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald DeJong","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2898,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.95245105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"296","last_page":"303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.980400025844574,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7398226261138916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6516584157943726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4667183756828308},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4166047275066376}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7398226261138916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6516584157943726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4667183756828308},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4166047275066376}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1390156.1390194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.6999","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.6999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icml2008.cs.helsinki.fi/papers/290.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1496855202","https://openalex.org/W1515851193","https://openalex.org/W1564812679","https://openalex.org/W1608333589","https://openalex.org/W1988217924","https://openalex.org/W1996625075","https://openalex.org/W2082691056","https://openalex.org/W2105235982","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2132602063","https://openalex.org/W2152828142","https://openalex.org/W2169186423","https://openalex.org/W2489939061","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4319773215","https://openalex.org/W4224287422","https://openalex.org/W4361026739","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4206669594","https://openalex.org/W3005560120","https://openalex.org/W3037422413"],"abstract_inverted_index":{"When":[0],"the":[1,18,25,51,66,68,71,74,89,95,104],"transition":[2,29],"probabilities":[3,30],"and":[4,46,81,113],"rewards":[5],"of":[6,50,65,73,91],"a":[7,44],"Markov":[8],"Decision":[9],"Process":[10],"(MDP)":[11],"are":[12,31],"known,":[13],"an":[14,41],"agent":[15,42,69],"can":[16],"obtain":[17],"optimal":[19,75,96],"policy":[20,76,97],"without":[21],"any":[22],"interaction":[23],"with":[24],"environment.":[26,52],"However,":[27],"exact":[28],"difficult":[32],"for":[33],"experts":[34],"to":[35,40,77,93],"specify.":[36],"One":[37],"option":[38],"left":[39],"is":[43,98],"long":[45],"potentially":[47],"costly":[48],"exploration":[49,87,106],"In":[53],"this":[54],"paper,":[55],"we":[56],"propose":[57],"another":[58],"alternative:":[59],"given":[60],"initial":[61],"(possibly":[62],"inaccurate)":[63],"specification":[64],"MDP,":[67],"determines":[70],"sensitivity":[72],"changes":[78],"in":[79],"transitions":[80],"rewards.":[82],"It":[83],"then":[84],"focuses":[85],"its":[86],"on":[88,110],"regions":[90],"space":[92],"which":[94],"most":[99],"sensitive.":[100],"We":[101],"show":[102],"that":[103],"proposed":[105],"strategy":[107],"performs":[108],"well":[109],"several":[111],"control":[112],"planning":[114],"problems.":[115]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}