{"id":"https://openalex.org/W4315471981","doi":"https://doi.org/10.1109/cdc51059.2022.9992857","title":"Deterministic Sequencing of Exploration and Exploitation for Reinforcement Learning","display_name":"Deterministic Sequencing of Exploration and Exploitation for Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315471981","doi":"https://doi.org/10.1109/cdc51059.2022.9992857"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992857","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992857","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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/A5103124832","display_name":"Piyush Gupta","orcid":"https://orcid.org/0000-0002-5141-2406"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Piyush Gupta","raw_affiliation_strings":["Michigan State University,Department of Electrical and Computer Engineering,East Lansing,Michigan,USA,48824"],"affiliations":[{"raw_affiliation_string":"Michigan State University,Department of Electrical and Computer Engineering,East Lansing,Michigan,USA,48824","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085821818","display_name":"Vaibhav Srivastava","orcid":"https://orcid.org/0000-0002-9786-0159"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhav Srivastava","raw_affiliation_strings":["Michigan State University,Department of Electrical and Computer Engineering,East Lansing,Michigan,USA,48824"],"affiliations":[{"raw_affiliation_string":"Michigan State University,Department of Electrical and Computer Engineering,East Lansing,Michigan,USA,48824","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103124832"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":0.3138,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53951344,"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":"2313","last_page":"2318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T12761","display_name":"Data Stream Mining Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8360264301300049},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7756330370903015},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7153053283691406},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.6705360412597656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6355054378509521},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5419585704803467},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5207733511924744},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.451813280582428},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41548585891723633},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.411828875541687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37307360768318176},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3255189061164856},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.218548983335495},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10796526074409485}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8360264301300049},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7756330370903015},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7153053283691406},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.6705360412597656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6355054378509521},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5419585704803467},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5207733511924744},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.451813280582428},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41548585891723633},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.411828875541687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37307360768318176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3255189061164856},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.218548983335495},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10796526074409485},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992857","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992857","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W21934178","https://openalex.org/W1965418165","https://openalex.org/W1983181247","https://openalex.org/W1988526405","https://openalex.org/W2028548064","https://openalex.org/W2052631868","https://openalex.org/W2150328967","https://openalex.org/W2155153696","https://openalex.org/W2168565265","https://openalex.org/W2265908272","https://openalex.org/W2781786131","https://openalex.org/W2787969715","https://openalex.org/W2962748815","https://openalex.org/W2964146343","https://openalex.org/W2964204801","https://openalex.org/W2972390852","https://openalex.org/W2973229164","https://openalex.org/W3020125231","https://openalex.org/W3206303178","https://openalex.org/W4205234789","https://openalex.org/W4206530644","https://openalex.org/W4211030719","https://openalex.org/W4214717370","https://openalex.org/W4287824277","https://openalex.org/W4298023569","https://openalex.org/W4315471981","https://openalex.org/W4388516305","https://openalex.org/W6601780888","https://openalex.org/W6604362843","https://openalex.org/W6634649043","https://openalex.org/W6639039794","https://openalex.org/W6675130772","https://openalex.org/W6774889137","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W1925875298","https://openalex.org/W4292701710","https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W4400868993","https://openalex.org/W1850488217","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W3096874164","https://openalex.org/W3182614517"],"abstract_inverted_index":{"We":[0,77],"propose":[1],"Deterministic":[2],"Sequencing":[3],"of":[4,60,81,97],"Exploration":[5],"and":[6,13,34,45,52,64,84],"Exploitation":[7],"(DSEE)":[8],"algorithm":[9],"with":[10,74],"interleaving":[11],"exploration":[12,83],"exploitation":[14,85],"epochs":[15,86],"for":[16,49],"model-based":[17],"RL":[18],"problems":[19],"that":[20,88],"aim":[21],"to":[22,69],"simultaneously":[23],"learn":[24],"the":[25,35,43,47,57,61,79,82,89],"system":[26],"model,":[27],"i.e.,":[28],"a":[29,71,94],"Markov":[30],"decision":[31],"process":[32],"(MDP),":[33],"associated":[36],"optimal":[37],"policy.":[38],"During":[39,55],"exploration,":[40],"DSEE":[41],"explores":[42],"environment":[44],"updates":[46],"estimates":[48,59],"expected":[50,62],"reward":[51,63],"transition":[53,65],"probabilities.":[54],"exploitation,":[56],"latest":[58],"probabilities":[66],"are":[67],"used":[68],"obtain":[70],"robust":[72],"policy":[73],"high":[75],"probability.":[76],"design":[78],"lengths":[80],"such":[87],"cumulative":[90],"regret":[91],"grows":[92],"as":[93],"sub-linear":[95],"function":[96],"time.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}