{"id":"https://openalex.org/W2108529574","doi":null,"title":"Learning to Explore and Exploit in POMDPs","display_name":"Learning to Explore and Exploit in POMDPs","publication_year":2009,"publication_date":"2009-12-07","ids":{"openalex":"https://openalex.org/W2108529574","mag":"2108529574"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.8656","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.8656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.duke.edu/~lcarin/LearnE2_NIPS09_22_FINAL.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"C. Cai","orcid":"https://orcid.org/0000-0003-3437-4820","observed_orcids":["https://orcid.org/0000-0003-3437-4820"]},"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":"C. Cai","raw_affiliation_strings":["Duke University"],"raw_orcid":"https://orcid.org/0000-0003-3437-4820","affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109304035","display_name":"Xuejun Liao","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":"Xuejun Liao","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016448581","display_name":"Lawrence Carin","orcid":"https://orcid.org/0000-0001-6277-7948","observed_orcids":["https://orcid.org/0000-0001-6277-7948"]},"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":"Lawrence Carin","raw_affiliation_strings":["Duke University"],"raw_orcid":"https://orcid.org/0000-0001-6277-7948","affiliations":[{"raw_affiliation_string":"Duke University","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":1.8046,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8713987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"22","issue":null,"first_page":"198","last_page":"206"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":9.999999747378752e-05,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.859000027179718},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.9710000157356262},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.8640000224113464},{"id":"https://openalex.org/keywords/oracle-queries","display_name":"oracle queries","score":0.4869999885559082},{"id":"https://openalex.org/keywords/partially-observable-environments","display_name":"partially observable environments","score":0.7630000114440918},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6190000176429749},{"id":"https://openalex.org/keywords/optimality-guarantees","display_name":"optimality guarantees","score":0.6549999713897705}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.8678498268127441},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8135062456130981},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7943320274353027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885692119598389},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.663112461566925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453216016292572},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4151898920536041},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10262316465377808},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07474854588508606},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.8656","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.8656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.duke.edu/~lcarin/LearnE2_NIPS09_22_FINAL.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.7581","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.7581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips22/NIPS2009_1107.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.889.6442","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.889.6442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/3814-learning-to-explore-and-exploit-in-pomdps.pdf","raw_type":"text"},{"id":"mag:2108529574","doi":null,"is_oa":false,"landing_page_url":"http://ece.duke.edu/~lcarin/LearnE2_NIPS09_22_FINAL.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","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":11,"referenced_works":["https://openalex.org/W1505937442","https://openalex.org/W1515851193","https://openalex.org/W1532688806","https://openalex.org/W1539216098","https://openalex.org/W1554015367","https://openalex.org/W2114235770","https://openalex.org/W2115979064","https://openalex.org/W2121863487","https://openalex.org/W2135681007","https://openalex.org/W2158640361","https://openalex.org/W3023407077"],"related_works":["https://openalex.org/W7095190760","https://openalex.org/W2128098349","https://openalex.org/W2290302229","https://openalex.org/W2408394588","https://openalex.org/W4413766826","https://openalex.org/W3004707083","https://openalex.org/W2096258902","https://openalex.org/W7133223817","https://openalex.org/W2404879558","https://openalex.org/W1526144783"],"abstract_inverted_index":{"A":[0],"fundamental":[1],"objective":[2],"in":[3,54,63,78],"reinforcement":[4],"learning":[5,44],"is":[6,102,127],"the":[7,23,29,45,49,65,73,80,94,99,105,113,116,125],"maintenance":[8],"of":[9,31,98,115,118,124],"a":[10,39],"proper":[11],"balance":[12,50],"between":[13,51],"exploration":[14,52,101,119],"and":[15,48,75,120],"exploitation.":[16,121],"This":[17],"problem":[18],"becomes":[19],"more":[20],"chal-lenging":[21],"when":[22],"agent":[24,46,66,81],"can":[25],"only":[26],"partially":[27,55],"observe":[28],"states":[30],"its":[32],"environment.":[33],"In":[34],"this":[35],"paper":[36],"we":[37],"propose":[38],"dual-policy":[40],"method":[41,59,126],"for":[42,85,92],"jointly":[43],"be-havior":[47],"exploitation,":[53],"observable":[56],"environments.":[57],"The":[58,96,122],"subsumes":[60],"traditional":[61],"exploration,":[62],"which":[64,79],"takes":[67],"actions":[68,87],"to":[69],"gather":[70],"information":[71],"about":[72],"environment,":[74],"active":[76],"learning,":[77],"queries":[82],"an":[83,89],"oracle":[84],"optimal":[86],"(with":[88],"associated":[90],"cost":[91],"employing":[93],"oracle).":[95],"form":[97],"employed":[100],"dictated":[103],"by":[104,129],"specific":[106],"problem.":[107],"Theoretical":[108],"guarantees":[109],"are":[110],"provided":[111],"concerning":[112],"optimality":[114],"balancing":[117],"effectiveness":[123],"demonstrated":[128],"experimental":[130],"results":[131],"on":[132],"benchmark":[133],"problems.":[134],"1":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}