{"id":"https://openalex.org/W2112899086","doi":"https://doi.org/10.1145/1553374.1553406","title":"The adaptive <i>k</i> -meteorologists problem and its application to structure learning and feature selection in reinforcement learning","display_name":"The adaptive <i>k</i> -meteorologists problem and its application to structure learning and feature selection in reinforcement learning","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2112899086","doi":"https://doi.org/10.1145/1553374.1553406","mag":"2112899086"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","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/A5051391610","display_name":"Carlos Diuk","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carlos Diuk","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711454","display_name":"Lihong Li","orcid":"https://orcid.org/0000-0002-5440-8242"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lihong Li","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029142872","display_name":"Bethany R. Leffler","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bethany R. Leffler","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051391610"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":9.9112,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.98153528,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9995999932289124,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9995999932289124,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9976000189781189,"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":0.8750061988830566},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6920906901359558},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6360191106796265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6335090398788452},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5924552083015442},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5885792374610901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5806418657302856},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5371999740600586},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47718656063079834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41127872467041016},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35021495819091797},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3461526930332184},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22426873445510864}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8750061988830566},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6920906901359558},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6360191106796265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6335090398788452},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5924552083015442},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5885792374610901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5806418657302856},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47718656063079834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41127872467041016},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35021495819091797},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3461526930332184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22426873445510864},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1553374.1553406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1819183015","display_name":null,"funder_award_id":"IIS-0713435","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G2563887035","display_name":null,"funder_award_id":"DGE 0549115","funder_id":"https://openalex.org/F4320337368","funder_display_name":"Division of Graduate Education"},{"id":"https://openalex.org/G440206934","display_name":null,"funder_award_id":"FA8750-05-2-0249","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W183249136","https://openalex.org/W1505937442","https://openalex.org/W1537180453","https://openalex.org/W1554015367","https://openalex.org/W1952404018","https://openalex.org/W1979675141","https://openalex.org/W2019363670","https://openalex.org/W2020294948","https://openalex.org/W2056957301","https://openalex.org/W2061504687","https://openalex.org/W2082691056","https://openalex.org/W2119567691","https://openalex.org/W2129192653","https://openalex.org/W2129670787","https://openalex.org/W2132876566","https://openalex.org/W2147071755","https://openalex.org/W2154347416","https://openalex.org/W2159810454","https://openalex.org/W2334782222","https://openalex.org/W2489939061","https://openalex.org/W2610818722","https://openalex.org/W2964117027","https://openalex.org/W3003579343","https://openalex.org/W3004360271","https://openalex.org/W3103882218","https://openalex.org/W4235825416","https://openalex.org/W4238893454","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2397544591","https://openalex.org/W4376639527","https://openalex.org/W1991417304","https://openalex.org/W2132876566","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W1969276875","https://openalex.org/W4310614650","https://openalex.org/W4386738330","https://openalex.org/W2788738055"],"abstract_inverted_index":{"The":[0,87],"purpose":[1],"of":[2,14,27,89],"this":[3,48],"paper":[4],"is":[5,50,92],"three-fold.":[6],"First,":[7],"we":[8,71],"formalize":[9],"and":[10,41],"study":[11],"a":[12,43,54,79,96,103],"problem":[13],"learning":[15],"probabilistic":[16],"concepts":[17],"in":[18,82,95],"the":[19,32,66,73],"recently":[20],"proposed":[21],"KWIK":[22],"framework.":[23],"We":[24],"give":[25,42],"details":[26],"an":[28,83],"algorithm,":[29],"known":[30],"as":[31,100,102],"Adaptive":[33,74],"k-Meteorologists":[34,75],"Algorithm,":[35],"analyze":[36],"its":[37],"sample-complexity":[38],"upper":[39],"bound,":[40],"matching":[44],"lower":[45],"bound.":[46],"Second,":[47],"algorithm":[49,57],"used":[51],"to":[52,77],"create":[53],"new":[55],"reinforcement-learning":[56,85],"for":[58],"factored-state":[59],"problems":[60],"that":[61],"enjoys":[62],"significant":[63],"improvement":[64],"over":[65],"previous":[67],"state-of-the-art":[68],"algorithm.":[69,86],"Finally,":[70],"apply":[72],"Algorithm":[76],"remove":[78],"limiting":[80],"assumption":[81],"existing":[84],"effectiveness":[88],"our":[90],"approaches":[91],"demonstrated":[93],"empirically":[94],"couple":[97],"benchmark":[98],"domains":[99],"well":[101],"robotics":[104],"navigation":[105],"problem.":[106]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}