{"id":"https://openalex.org/W2098152875","doi":"https://doi.org/10.1145/1390156.1390199","title":"Reinforcement learning in the presence of rare events","display_name":"Reinforcement learning in the presence of rare events","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2098152875","doi":"https://doi.org/10.1145/1390156.1390199","mag":"2098152875"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390199","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.82308/25521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113700180","display_name":"Jordan Frank","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jordan Frank","raw_affiliation_strings":["McGill University\u2028Montreal, Quebec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University\u2028Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["McGill University\u2028Montreal, Quebec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University\u2028Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["McGill University\u2028Montreal, Quebec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University\u2028Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":2.3349,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.89946408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"336","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9876999855041504,"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/T11031","display_name":"Game Theory and Applications","score":0.9868999719619751,"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":0.8195432424545288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6578847169876099},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6327534317970276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3871088922023773},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1708604395389557},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06850606203079224}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8195432424545288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6578847169876099},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6327534317970276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3871088922023773},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1708604395389557},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06850606203079224}],"mesh":[],"locations_count":10,"locations":[{"id":"doi:10.1145/1390156.1390199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390199","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:doi:10.82308/25521","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14905/114599","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"https://vocabularies.coar-repositories.org/resource_types/c_46ec/"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.4737","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4737","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/580.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.180.1809","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.180.1809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.mcgill.ca/%7Eshie/public/C-FrankMPrecup-ICML2008.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.224.9329","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.224.9329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/%7Ejfrank8/pubs/jordan-frank-masters-thesis.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.917.7727","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.917.7727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Doina_Precup/publication/221344808_Reinforcement_learning_in_the_presence_of_rare_events/links/0912f51191d817d910000000.pdf","raw_type":"text"},{"id":"pmh:oai:collectionscanada.gc.ca:QMM.111576","is_oa":false,"landing_page_url":"http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=111576","pdf_url":null,"source":{"id":"https://openalex.org/S4306402307","display_name":"Library and Archives Canada (Government of Canada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802286613","host_organization_name":"Government of Canada","host_organization_lineage":["https://openalex.org/I2802286613"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Electronic Thesis or Dissertation"},{"id":"pmh:oai:digitool.library.mcgill.ca:111576","is_oa":false,"landing_page_url":"http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=111576","pdf_url":null,"source":{"id":"https://openalex.org/S4306401568","display_name":"eScholarship@McGill (McGill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5023651","host_organization_name":"McGill University","host_organization_lineage":["https://openalex.org/I5023651"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Electronic Thesis or Dissertation"},{"id":"pmh:oai:escholarship.mcgill.ca:m613n219z","is_oa":false,"landing_page_url":"https://escholarship.mcgill.ca/concern/theses/m613n219z","pdf_url":null,"source":{"id":"https://openalex.org/S4306401568","display_name":"eScholarship@McGill (McGill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5023651","host_organization_name":"McGill University","host_organization_lineage":["https://openalex.org/I5023651"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"doi:10.82308/25521","is_oa":true,"landing_page_url":"https://doi.org/10.82308/25521","pdf_url":null,"source":{"id":"https://openalex.org/S7407060097","display_name":"McGill-DEV","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dissertation"}],"best_oa_location":{"id":"doi:10.82308/25521","is_oa":true,"landing_page_url":"https://doi.org/10.82308/25521","pdf_url":null,"source":{"id":"https://openalex.org/S7407060097","display_name":"McGill-DEV","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W155952036","https://openalex.org/W242065599","https://openalex.org/W1488730473","https://openalex.org/W1496357020","https://openalex.org/W1499021337","https://openalex.org/W1502364872","https://openalex.org/W1514587017","https://openalex.org/W1525685818","https://openalex.org/W1545262042","https://openalex.org/W1576452626","https://openalex.org/W1585546214","https://openalex.org/W1600046456","https://openalex.org/W1608666872","https://openalex.org/W1621653743","https://openalex.org/W1778554682","https://openalex.org/W1994616650","https://openalex.org/W1994974369","https://openalex.org/W2003732947","https://openalex.org/W2004224914","https://openalex.org/W2012036715","https://openalex.org/W2014512216","https://openalex.org/W2015399216","https://openalex.org/W2039348752","https://openalex.org/W2051203581","https://openalex.org/W2051277798","https://openalex.org/W2052147111","https://openalex.org/W2060859869","https://openalex.org/W2076487594","https://openalex.org/W2087018957","https://openalex.org/W2100677568","https://openalex.org/W2102000945","https://openalex.org/W2104641222","https://openalex.org/W2107726111","https://openalex.org/W2108114251","https://openalex.org/W2108682071","https://openalex.org/W2108692343","https://openalex.org/W2113913482","https://openalex.org/W2115264563","https://openalex.org/W2117341272","https://openalex.org/W2119879106","https://openalex.org/W2121863487","https://openalex.org/W2126565096","https://openalex.org/W2130985368","https://openalex.org/W2146416787","https://openalex.org/W2147967768","https://openalex.org/W2153551324","https://openalex.org/W2158126207","https://openalex.org/W2158361345","https://openalex.org/W2158548602","https://openalex.org/W2159951376","https://openalex.org/W2164863330","https://openalex.org/W2167019781","https://openalex.org/W2167574525","https://openalex.org/W2204171025","https://openalex.org/W2341171179","https://openalex.org/W2725430436","https://openalex.org/W2787259794","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3023407077","https://openalex.org/W3103182070","https://openalex.org/W3139377883","https://openalex.org/W3215037115","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2038908348","https://openalex.org/W1977959518","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571"],"abstract_inverted_index":{"Learning":[0],"agents":[1],"often":[2],"find":[3],"themselves":[4],"in":[5,7,43,55,59,112,133],"environments":[6],"which":[8,60],"rare":[9,65,97],"significant":[10],"events":[11,25,66],"occur":[12],"independently":[13],"of":[14,18,31,63,88,124,136],"their":[15,28,125,131],"current":[16],"choice":[17],"action.":[19],"Traditional":[20],"reinforcement":[21],"learning":[22,52],"algorithms":[23,74,93,119],"sample":[24],"according":[26],"to":[27,36,100,108],"natural":[29],"probability":[30,62],"occurring,":[32],"and":[33,40,79,84,104,127,129],"therefore":[34],"tend":[35],"exhibit":[37],"slow":[38],"convergence":[39],"high":[41],"variance":[42,103],"such":[44],"environments.":[45],"In":[46],"this":[47],"thesis,":[48],"we":[49],"assume":[50],"that":[51,117],"is":[53],"done":[54],"a":[56,134,139],"simulated":[57],"environment":[58],"the":[61,89,96,102,113],"these":[64,118],"can":[67],"be":[68],"artificially":[69],"altered.":[70],"We":[71,115],"present":[72],"novel":[73],"for":[75,110],"both":[76,82],"policy":[77],"evaluation":[78],"control,":[80],"using":[81],"tabular":[83],"function":[85],"approximation":[86],"representations":[87],"value":[90],"function.":[91],"These":[92],"automatically":[94],"tune":[95],"event":[98],"probabilities":[99],"minimize":[101],"use":[105],"importance":[106],"sampling":[107],"correct":[109],"changes":[111],"dynamics.":[114],"prove":[116],"converge,":[120],"provide":[121],"an":[122],"analysis":[123],"bias":[126],"variance,":[128],"demonstrate":[130],"utility":[132],"number":[135],"domains,":[137],"including":[138],"large":[140],"network":[141],"planning":[142],"task.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}