{"id":"https://openalex.org/W4236243725","doi":"https://doi.org/10.1007/bf00115298","title":"Exploration bonuses and dual control","display_name":"Exploration bonuses and dual control","publication_year":1996,"publication_date":"1996-10-01","ids":{"openalex":"https://openalex.org/W4236243725","doi":"https://doi.org/10.1007/bf00115298"},"language":"en","primary_location":{"id":"doi:10.1007/bf00115298","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00115298","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00115298.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/BF00115298.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075063030","display_name":"Peter Dayan","orcid":"https://orcid.org/0000-0003-3476-1839"},"institutions":[{"id":"https://openalex.org/I4210104429","display_name":"Institute of Cognitive and Brain Sciences","ror":"https://ror.org/01c3w3270","country_code":"US","type":"education","lineage":["https://openalex.org/I4210104429"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peter Dayan","raw_affiliation_strings":["CBCL, Department of Brain and Cognitive Science, E25-210, MIT, 02139, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"CBCL, Department of Brain and Cognitive Science, E25-210, MIT, 02139, Cambridge, MA","institution_ids":["https://openalex.org/I4210104429"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044141636","display_name":"Terrence J. Sejnowski","orcid":"https://orcid.org/0000-0002-0622-7391"},"institutions":[{"id":"https://openalex.org/I1307098950","display_name":"Salk Institute for Biological Studies","ror":"https://ror.org/03xez1567","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1307098950"]},{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Terrence J. Sejnowski","raw_affiliation_strings":["Department of Biology, University of California at San Diego, 92093, La Jolla, CA","Howard Hughes Medical Institute, The Salk Institute, PO Box 85800, 92186-5800, San Diego, CA"],"affiliations":[{"raw_affiliation_string":"Department of Biology, University of California at San Diego, 92093, La Jolla, CA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Howard Hughes Medical Institute, The Salk Institute, PO Box 85800, 92186-5800, San Diego, CA","institution_ids":["https://openalex.org/I1307098950","https://openalex.org/I1344073410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075063030"],"corresponding_institution_ids":["https://openalex.org/I4210104429"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.845,"has_fulltext":true,"cited_by_count":71,"citation_normalized_percentile":{"value":0.79943293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":"1","first_page":"5","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9930999875068665,"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":0.9708999991416931,"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":0.7157139778137207},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6455806493759155},{"id":"https://openalex.org/keywords/certainty","display_name":"Certainty","score":0.5484850406646729},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5157842636108398},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5032269358634949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5026102066040039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48401352763175964},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.4682900309562683},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4589558243751526},{"id":"https://openalex.org/keywords/miller","display_name":"Miller","score":0.4458756446838379},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4057524800300598},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35467860102653503},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3183150291442871}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7157139778137207},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6455806493759155},{"id":"https://openalex.org/C7493553","wikidata":"https://www.wikidata.org/wiki/Q1520777","display_name":"Certainty","level":2,"score":0.5484850406646729},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5157842636108398},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5032269358634949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5026102066040039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48401352763175964},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4682900309562683},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4589558243751526},{"id":"https://openalex.org/C2777496998","wikidata":"https://www.wikidata.org/wiki/Q1536587","display_name":"Miller","level":2,"score":0.4458756446838379},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4057524800300598},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35467860102653503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3183150291442871},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1007/bf00115298","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00115298","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00115298.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.164.3455","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.164.3455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.cnl.salk.edu/PDFs/Exploration Bonuses and Dual Control 1996-3652.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.32.4207","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.4207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.ai.mit.edu/pub/users/dayan/papers/exp.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.56.5312","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.56.5312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.toronto.edu/pub/dayan/exp.ps.Z","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.99.9831","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.99.9831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gatsby.ucl.ac.uk/~dayan/papers/ds96.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:85069","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/85069/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   MACH LEARN , 25  (1)   5 - 22.   (1996)      ","raw_type":"Article"},{"id":"pmh:oai:pure.mpg.de:item_3022448","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0002-D65D-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/bf00115298","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00115298","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00115298.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306082","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4236243725.pdf","grobid_xml":"https://content.openalex.org/works/W4236243725.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W132264163","https://openalex.org/W342056545","https://openalex.org/W354832773","https://openalex.org/W1491843047","https://openalex.org/W1529558080","https://openalex.org/W1973788679","https://openalex.org/W1982997797","https://openalex.org/W1993192904","https://openalex.org/W1994306069","https://openalex.org/W2003381716","https://openalex.org/W2009533501","https://openalex.org/W2028145673","https://openalex.org/W2065087844","https://openalex.org/W2099724000","https://openalex.org/W2123651102","https://openalex.org/W2123967330","https://openalex.org/W2346626577","https://openalex.org/W2598912124","https://openalex.org/W3103871524","https://openalex.org/W3149349937","https://openalex.org/W4233151592","https://openalex.org/W4252450337","https://openalex.org/W6602690695","https://openalex.org/W6623622288","https://openalex.org/W6631000544","https://openalex.org/W6636530465","https://openalex.org/W6670523119","https://openalex.org/W6675901991","https://openalex.org/W6681490538","https://openalex.org/W6775686901","https://openalex.org/W7054112703"],"related_works":["https://openalex.org/W3036113924","https://openalex.org/W3155555900","https://openalex.org/W2058016970","https://openalex.org/W3187290648","https://openalex.org/W4233121562","https://openalex.org/W3034420249","https://openalex.org/W4230008669","https://openalex.org/W2900582745","https://openalex.org/W1926181953","https://openalex.org/W2418227039"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}