{"id":"https://openalex.org/W2058455325","doi":"https://doi.org/10.1109/cdc.2011.6160851","title":"TD-learning with exploration","display_name":"TD-learning with exploration","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2058455325","doi":"https://doi.org/10.1109/cdc.2011.6160851","mag":"2058455325"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2011.6160851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2011.6160851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Conference on Decision and Control and European Control Conference","raw_type":"proceedings-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/A5047988825","display_name":"Sean Meyn","orcid":"https://orcid.org/0000-0002-8558-365X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sean P. Meyn","raw_affiliation_strings":["Department of Electrical and Computer Engineering and the Coordinated Science Laboratory, UIUC, USA","Department of Electrical and Computer Engineering and the Coordinated Science Laboratory at UIUC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Coordinated Science Laboratory, UIUC, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Coordinated Science Laboratory at UIUC, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054958460","display_name":"Amit Surana","orcid":"https://orcid.org/0000-0002-6409-5139"},"institutions":[{"id":"https://openalex.org/I4210136752","display_name":"University Transportation Research Center","ror":"https://ror.org/03pz4a950","country_code":"US","type":"other","lineage":["https://openalex.org/I4210136752"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Surana","raw_affiliation_strings":["United Technologies Research Center, Inc., USA","United Technologies Research Center (UTRC), USA"],"affiliations":[{"raw_affiliation_string":"United Technologies Research Center, Inc., USA","institution_ids":[]},{"raw_affiliation_string":"United Technologies Research Center (UTRC), USA","institution_ids":["https://openalex.org/I4210136752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047988825"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.15450933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"134","issue":null,"first_page":"148","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9941999912261963,"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":0.9941999912261963,"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":0.9883000254631042,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.6063029170036316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34476524591445923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6063029170036316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34476524591445923}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc.2011.6160851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2011.6160851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Conference on Decision and Control and European Control Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.7797","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.7797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.meyn.ece.ufl.edu/archive/spm_files/Papers_pdf/SARSA%2BTDwithExploration_submitted.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W163688550","https://openalex.org/W565357261","https://openalex.org/W594357522","https://openalex.org/W1569320505","https://openalex.org/W1576452626","https://openalex.org/W1745373831","https://openalex.org/W1979500760","https://openalex.org/W1980019479","https://openalex.org/W1983321045","https://openalex.org/W1991470928","https://openalex.org/W1995713768","https://openalex.org/W1998172110","https://openalex.org/W2001015965","https://openalex.org/W2014320009","https://openalex.org/W2034039215","https://openalex.org/W2073384958","https://openalex.org/W2086161653","https://openalex.org/W2109762954","https://openalex.org/W2110097348","https://openalex.org/W2122945138","https://openalex.org/W2138238306","https://openalex.org/W2139418546","https://openalex.org/W2146524676","https://openalex.org/W2150339816","https://openalex.org/W2151661095","https://openalex.org/W2160698719","https://openalex.org/W2165469059","https://openalex.org/W2168483803","https://openalex.org/W2480373768","https://openalex.org/W2548693888","https://openalex.org/W2959560348","https://openalex.org/W3011120880","https://openalex.org/W3124066568","https://openalex.org/W3139377883","https://openalex.org/W4205326910","https://openalex.org/W4211221179","https://openalex.org/W4243772471","https://openalex.org/W4302097244","https://openalex.org/W6678313319","https://openalex.org/W6729950211","https://openalex.org/W6792155000"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,38],"introduce":[1],"exploration":[2],"in":[3,34,51],"the":[4,9,22,35,46,56,67],"TD-learning":[5],"algorithm":[6,57],"to":[7,29,42,44],"approximate":[8],"value":[10],"function":[11],"for":[12,25,48],"a":[13,30],"given":[14],"policy.":[15],"In":[16],"this":[17],"way":[18],"we":[19],"can":[20],"modify":[21],"norm":[23],"used":[24],"approximation,":[26],"\u201czooming":[27],"in\u201d":[28],"region":[31],"of":[32,55,70],"interest":[33],"state":[36],"space.":[37],"also":[39],"provide":[40],"extensions":[41],"SARSA":[43],"eliminate":[45],"need":[47],"numerical":[49],"integration":[50],"policy":[52],"improvement.":[53],"Construction":[54],"and":[58,73],"its":[59],"analysis":[60],"build":[61],"on":[62],"recent":[63],"general":[64],"results":[65],"concerning":[66],"spectral":[68],"theory":[69],"Markov":[71],"chains":[72],"positive":[74],"operators.":[75]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}