{"id":"https://openalex.org/W2140332127","doi":"https://doi.org/10.1145/1143844.1143949","title":"An intrinsic reward mechanism for efficient exploration","display_name":"An intrinsic reward mechanism for efficient exploration","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2140332127","doi":"https://doi.org/10.1145/1143844.1143949","mag":"2140332127"},"language":"en","primary_location":{"id":"doi:10.1145/1143844.1143949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://scholarworks.umass.edu/bitstreams/8c59bbc9-e8ee-45c7-a122-5c53df6ca50b/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079000862","display_name":"\u00d6zg\u00fcr \u015eim\u015fek","orcid":"https://orcid.org/0000-0001-5449-0437"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"\u00d6zg\u00fcr \u015eim\u015fek","raw_affiliation_strings":["University of Massachusetts, Amherst, MA","University of Massachusetts, Amherst MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew G. Barto","raw_affiliation_strings":["University of Massachusetts, Amherst, MA","University of Massachusetts, Amherst MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079000862"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":7.9171,"has_fulltext":true,"cited_by_count":100,"citation_normalized_percentile":{"value":0.97246233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"833","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9904000163078308,"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/T12288","display_name":"Optimization and Search Problems","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8579288721084595},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7369563579559326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7359375357627869},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7302887439727783},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6647985577583313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5808234810829163},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5605162382125854},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5407711267471313},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5282788872718811},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5124421715736389},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5084611177444458},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5043357610702515},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46315398812294006},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4615374505519867},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3664681911468506},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3298863172531128},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2963767647743225},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13086017966270447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1249677836894989}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8579288721084595},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7369563579559326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7359375357627869},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7302887439727783},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6647985577583313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5808234810829163},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5605162382125854},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5407711267471313},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5282788872718811},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5124421715736389},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5084611177444458},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5043357610702515},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46315398812294006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4615374505519867},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3664681911468506},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3298863172531128},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2963767647743225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13086017966270447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1249677836894989},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1143844.1143949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1021","is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/4","pdf_url":"https://scholarworks.umass.edu/bitstreams/8c59bbc9-e8ee-45c7-a122-5c53df6ca50b/download","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:20.500.14394/10058","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14394/10058","pdf_url":null,"source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Article"},{"id":"pmh:oai:works.bepress.com:andrew_barto-1012","is_oa":false,"landing_page_url":"https://works.bepress.com/andrew_barto/13","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andrew G. Barto","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1021","is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/4","pdf_url":"https://scholarworks.umass.edu/bitstreams/8c59bbc9-e8ee-45c7-a122-5c53df6ca50b/download","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1951804731","display_name":"Collaborative Research:  Intrinsically Motivated Learning in Artificial Agents","funder_award_id":"0432143","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2140332127.pdf","grobid_xml":"https://content.openalex.org/works/W2140332127.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W119532227","https://openalex.org/W172298727","https://openalex.org/W1486707268","https://openalex.org/W1491843047","https://openalex.org/W1497039698","https://openalex.org/W1504212531","https://openalex.org/W1590585250","https://openalex.org/W1598052524","https://openalex.org/W1968768508","https://openalex.org/W2048226872","https://openalex.org/W2090170171","https://openalex.org/W2109910161","https://openalex.org/W2112483970","https://openalex.org/W2128775537","https://openalex.org/W2139612737","https://openalex.org/W2143435603","https://openalex.org/W2158823144","https://openalex.org/W2160808139","https://openalex.org/W2489939061","https://openalex.org/W3023407077"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3096874164","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779","https://openalex.org/W2386410636"],"abstract_inverted_index":{"How":[0],"should":[1,25],"a":[2,39,54,65,76,79],"reinforcement":[3],"learning":[4,75],"agent":[5,51],"act":[6],"if":[7],"its":[8,58,82],"sole":[9],"purpose":[10],"is":[11],"to":[12,28,31],"efficiently":[13],"learn":[14],"an":[15],"optimal":[16],"policy":[17,77],"for":[18,57,74,78],"later":[19],"use?":[20],"In":[21],"other":[22],"words,":[23],"how":[24],"it":[26],"explore,":[27],"be":[29],"able":[30],"exploit":[32],"later?":[33],"We":[34,60],"formulate":[35],"this":[36],"problem":[37],"as":[38],"Markov":[40],"Decision":[41],"Process":[42],"by":[43],"explicitly":[44],"modeling":[45],"the":[46,50,71],"internal":[47],"state":[48],"of":[49,67,89],"and":[52],"propose":[53],"principled":[55],"heuristic":[56],"solution.":[59],"present":[61],"experimental":[62],"results":[63],"in":[64],"number":[66],"domains,":[68],"also":[69],"exploring":[70],"algorithm's":[72],"use":[73],"skill":[80,90],"given":[81],"reward":[83],"function---an":[84],"important":[85],"but":[86],"neglected":[87],"component":[88],"discovery.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}