{"id":"https://openalex.org/W1492936035","doi":null,"title":"Algorithm Selection using Reinforcement Learning","display_name":"Algorithm Selection using Reinforcement Learning","publication_year":2000,"publication_date":"2000-06-29","ids":{"openalex":"https://openalex.org/W1492936035","mag":"1492936035"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.42.3255","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.42.3255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.duke.edu/~mgl/papers/icml00.ps.gz","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5084693234","display_name":"Michail G. Lagoudakis","orcid":"https://orcid.org/0000-0003-2803-3755","observed_orcids":["https://orcid.org/0000-0003-2803-3755"]},"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":"Michail G. Lagoudakis","raw_affiliation_strings":["Duke University"],"raw_orcid":"https://orcid.org/0000-0003-2803-3755","affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840","observed_orcids":["https://orcid.org/0000-0002-5596-1840"]},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["At&T#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-5596-1840","affiliations":[{"raw_affiliation_string":"At&T#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.3485,"has_fulltext":false,"cited_by_count":134,"citation_normalized_percentile":{"value":0.97566862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"511","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.638700008392334,"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":0.638700008392334,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.054099999368190765,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.04699999839067459,"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/algorithm-selection","display_name":"algorithm selection","score":0.9909999966621399},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9179999828338623},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.8169999718666077},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7699999809265137},{"id":"https://openalex.org/keywords/sorting","display_name":"sorting","score":0.7360000014305115},{"id":"https://openalex.org/keywords/execution-time-reduction","display_name":"execution time reduction","score":0.9340000152587891}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8272727131843567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263922095298767},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6694859266281128},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6377173662185669},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.524052619934082},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.5125329494476318},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48342883586883545},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.47080764174461365},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43240344524383545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4114255905151367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36286425590515137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35445162653923035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16328197717666626},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.42.3255","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.42.3255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.duke.edu/~mgl/papers/icml00.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.472.7494","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.472.7494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.duke.edu/research/AI/PAPERS/2000/icml00-algsel.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.6060","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.6060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.duke.edu/~mgl/papers/PDF/icml00.pdf","raw_type":"text"},{"id":"mag:1492936035","doi":null,"is_oa":false,"landing_page_url":"https://www.researchgate.net/profile/Michael_Littman2/publication/2871654_Algorithm_Selection_using_Reinforcement_Learning/links/54b66cba0cf2e68eb27e8a4e.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"International Conference on Machine Learning","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":7,"referenced_works":["https://openalex.org/W1597303641","https://openalex.org/W1714472976","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2124234772","https://openalex.org/W2125074935","https://openalex.org/W2752885492"],"related_works":["https://openalex.org/W1522248029","https://openalex.org/W2134014128","https://openalex.org/W2140519248","https://openalex.org/W1574658687","https://openalex.org/W7054795407","https://openalex.org/W4235585935","https://openalex.org/W2284991187","https://openalex.org/W1983840635","https://openalex.org/W1989547529","https://openalex.org/W1570754865"],"abstract_inverted_index":{"Many":[0],"computational":[1,155],"problems":[2,136],"can":[3],"be":[4],"solved":[5],"by":[6,83],"multiple":[7,85],"algorithms,":[8],"with":[9,40],"different":[10,14],"algorithms":[11],"fastest":[12],"for":[13,95],"problem":[15,25,39,52,82],"sizes,":[16],"input":[17],"distri-butions,":[18],"and":[19,61,105,113,141],"hardware":[20],"characteristics.":[21],"We":[22,49],"con-sider":[23],"the":[24,41,45,51,79,121,134,147],"of":[26,37,43,56,75,127,137,149],"algorithm":[27,32,80,92],"selection:":[28],"dy-namically":[29],"choose":[30],"an":[31,35],"to":[33,67,118,153],"attack":[34],"in-stance":[36],"a":[38,54,73,99,116],"goal":[42],"minimiz-ing":[44],"overall":[46],"execution":[47],"time.":[48],"formulate":[50],"as":[53],"kind":[55,74],"Markov":[57],"decision":[58],"process":[59],"(MDP),":[60],"use":[62],"ideas":[63],"from":[64],"reinforcement":[65],"learn-ing":[66],"solve":[68],"it.":[69],"This":[70],"paper":[71],"introduces":[72],"MDP":[76],"that":[77,101],"models":[78],"selection":[81,140],"allowing":[84],"state":[86],"transitions.":[87],"The":[88,129,143],"well":[89],"known":[90],"Q-learning":[91],"is":[93],"adapted":[94],"this":[96,110],"case":[97],"in":[98,115],"way":[100,117],"combines":[102],"both":[103],"Monte-Carlo":[104],"Temporal":[106,123],"Difference":[107,124],"methods.":[108],"Also,":[109],"work":[111],"uses,":[112],"extends":[114],"control":[119],"prob-lems,":[120],"Least-Squares":[122],"al-gorithm":[125],"(LSTD(0))":[126],"Boyan.":[128],"experimental":[130],"study":[131],"focuses":[132],"on":[133],"classic":[135],"order":[138],"statistic":[139],"sorting.":[142],"encouraging":[144],"results":[145],"reveal":[146],"potential":[148],"applying":[150],"learning":[151],"methods":[152],"traditional":[154],"problems.":[156],"1.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2016-06-24T00:00:00"}