{"id":"https://openalex.org/W2057050711","doi":"https://doi.org/10.1007/s00453-003-1038-1","title":"Reinforcement Learning with Immediate Rewards and Linear Hypotheses","display_name":"Reinforcement Learning with Immediate Rewards and Linear Hypotheses","publication_year":2003,"publication_date":"2003-09-30","ids":{"openalex":"https://openalex.org/W2057050711","doi":"https://doi.org/10.1007/s00453-003-1038-1","mag":"2057050711"},"language":"en","primary_location":{"id":"doi:10.1007/s00453-003-1038-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00453-003-1038-1","pdf_url":null,"source":{"id":"https://openalex.org/S89324355","display_name":"Algorithmica","issn_l":"0178-4617","issn":["0178-4617","1432-0541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithmica","raw_type":"journal-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/A5060856151","display_name":"Naoki Abe","orcid":"https://orcid.org/0000-0002-4048-3989"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Naoki Abe","raw_affiliation_strings":["IBM T. J. Watson Research Center,\nYorktown Heights, NY 10598, USA","IBM, T.J. Watson Research Center, Yorktown Heights, NY 10598"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center,\nYorktown Heights, NY 10598, USA","institution_ids":[]},{"raw_affiliation_string":"IBM, T.J. Watson Research Center, Yorktown Heights, NY 10598","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087979002","display_name":"Alan W. Biermann","orcid":null},"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":"Alan W. Biermann","raw_affiliation_strings":["Department of Computer Science, Duke University, P.O. Box 90129, Durham, NC 27708, USA","Department of Computer Science, Duke University, P.O. Box 90129, Durham, NC 27708"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Duke University, P.O. Box 90129, Durham, NC 27708, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Computer Science, Duke University, P.O. Box 90129, Durham, NC 27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084487318","display_name":"Philip M. Long","orcid":"https://orcid.org/0000-0002-1010-6197"},"institutions":[{"id":"https://openalex.org/I66068411","display_name":"Genome Institute of Singapore","ror":"https://ror.org/05k8wg936","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I2801752549","https://openalex.org/I66068411"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Philip M. Long","raw_affiliation_strings":["Genome Institute of Singapore, 1 Science Park Road, #05-01, Singapore 117528, Republic of Singapore","Genome Institute of Singapore, 1 Science Park Road, #05-01, Singapore 117528"],"affiliations":[{"raw_affiliation_string":"Genome Institute of Singapore, 1 Science Park Road, #05-01, Singapore 117528, Republic of Singapore","institution_ids":["https://openalex.org/I66068411"]},{"raw_affiliation_string":"Genome Institute of Singapore, 1 Science Park Road, #05-01, Singapore 117528","institution_ids":["https://openalex.org/I66068411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060856151"],"corresponding_institution_ids":[],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":0.8844,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.76891989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"37","issue":"4","first_page":"263","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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/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/T12072","display_name":"Machine Learning and Algorithms","score":0.9958000183105469,"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/regret","display_name":"Regret","score":0.6887211799621582},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5885512828826904},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5725820064544678},{"id":"https://openalex.org/keywords/infinity","display_name":"Infinity","score":0.5103544592857361},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.49118611216545105},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"Theory of computation","score":0.4774497151374817},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46856266260147095},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44882330298423767},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44075578451156616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.34962034225463867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3013759255409241},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23168501257896423},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18190282583236694}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6887211799621582},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5885512828826904},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5725820064544678},{"id":"https://openalex.org/C7321624","wikidata":"https://www.wikidata.org/wiki/Q205","display_name":"Infinity","level":2,"score":0.5103544592857361},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.49118611216545105},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.4774497151374817},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46856266260147095},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44882330298423767},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44075578451156616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34962034225463867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3013759255409241},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23168501257896423},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18190282583236694},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00453-003-1038-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00453-003-1038-1","pdf_url":null,"source":{"id":"https://openalex.org/S89324355","display_name":"Algorithmica","issn_l":"0178-4617","issn":["0178-4617","1432-0541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithmica","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.93.7666","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.93.7666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.ibm.com/people/n/nabe/AlgorithmicaABL.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W230545259","https://openalex.org/W1535810436","https://openalex.org/W1538558539","https://openalex.org/W1565914110","https://openalex.org/W1595135966","https://openalex.org/W1765479834","https://openalex.org/W1968444040","https://openalex.org/W1975690796","https://openalex.org/W1979675141","https://openalex.org/W1982381767","https://openalex.org/W1986842597","https://openalex.org/W2021801581","https://openalex.org/W2038390905","https://openalex.org/W2077902449","https://openalex.org/W2091401625","https://openalex.org/W2101467810","https://openalex.org/W2108114251","https://openalex.org/W2116067849","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2123981539","https://openalex.org/W2124846360","https://openalex.org/W2129113961","https://openalex.org/W2913292478","https://openalex.org/W3145837419"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W3123835761","https://openalex.org/W4292701710"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}