{"id":"https://openalex.org/W3183431726","doi":"https://doi.org/10.1109/cdc45484.2021.9683076","title":"Non-Markovian Reinforcement Learning using Fractional Dynamics","display_name":"Non-Markovian Reinforcement Learning using Fractional Dynamics","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W3183431726","doi":"https://doi.org/10.1109/cdc45484.2021.9683076","mag":"3183431726"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683076","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE 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":"2021 60th IEEE 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/A5077386816","display_name":"Gaurav Gupta","orcid":"https://orcid.org/0000-0002-5192-4428"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gaurav Gupta","raw_affiliation_strings":["Univ. of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,USA"],"affiliations":[{"raw_affiliation_string":"Univ. of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037487522","display_name":"Chenzhong Yin","orcid":"https://orcid.org/0000-0001-6411-7441"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenzhong Yin","raw_affiliation_strings":["Univ. of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,USA"],"affiliations":[{"raw_affiliation_string":"Univ. of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057473400","display_name":"Jyotirmoy V. Deshmukh","orcid":"https://orcid.org/0000-0003-4683-5540"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyotirmoy V. Deshmukh","raw_affiliation_strings":["Univ. of Southern California,Department of Computer Science,Los Angeles,CA,USA"],"affiliations":[{"raw_affiliation_string":"Univ. of Southern California,Department of Computer Science,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105925385","display_name":"Paul Bogdan","orcid":"https://orcid.org/0000-0003-2118-0816"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Bogdan","raw_affiliation_strings":["Univ. of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,USA"],"affiliations":[{"raw_affiliation_string":"Univ. of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077386816"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":3.6315,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93959108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1542","last_page":"1547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9861000180244446,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8735617399215698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6834431886672974},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6022336483001709},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5715863108634949},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.511242151260376},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5027596950531006},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4733733534812927},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.4519313871860504},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43605631589889526},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36309516429901123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36232975125312805},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22416821122169495},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22289729118347168},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18289679288864136}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8735617399215698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6834431886672974},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6022336483001709},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5715863108634949},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.511242151260376},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5027596950531006},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4733733534812927},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.4519313871860504},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43605631589889526},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36309516429901123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36232975125312805},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22416821122169495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22289729118347168},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18289679288864136},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683076","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE 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":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W85516124","https://openalex.org/W1503120371","https://openalex.org/W1571472016","https://openalex.org/W1747856733","https://openalex.org/W1850511188","https://openalex.org/W1972871522","https://openalex.org/W1998561306","https://openalex.org/W2014120095","https://openalex.org/W2034725503","https://openalex.org/W2062962812","https://openalex.org/W2074500080","https://openalex.org/W2076337359","https://openalex.org/W2092165479","https://openalex.org/W2109910161","https://openalex.org/W2117343462","https://openalex.org/W2121346710","https://openalex.org/W2123447947","https://openalex.org/W2158782408","https://openalex.org/W2158796564","https://openalex.org/W2159434869","https://openalex.org/W2163785392","https://openalex.org/W2167160009","https://openalex.org/W2288809108","https://openalex.org/W2546571074","https://openalex.org/W2558819991","https://openalex.org/W2587954981","https://openalex.org/W2620552042","https://openalex.org/W2787933113","https://openalex.org/W2808418668","https://openalex.org/W2902723719","https://openalex.org/W2962872206","https://openalex.org/W2963335520","https://openalex.org/W2963791186","https://openalex.org/W2963960193","https://openalex.org/W2972732693","https://openalex.org/W2993025150","https://openalex.org/W2997022832","https://openalex.org/W3008110675","https://openalex.org/W3097668739","https://openalex.org/W3110922453","https://openalex.org/W3120740533","https://openalex.org/W3136466665","https://openalex.org/W4298206671","https://openalex.org/W4315575041","https://openalex.org/W4394639584","https://openalex.org/W4394644466","https://openalex.org/W6678481081","https://openalex.org/W6730531408","https://openalex.org/W6751494529","https://openalex.org/W6771603063","https://openalex.org/W6791543022","https://openalex.org/W6863616840"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3,149],"a":[4,17,78,83,118,141,152,189],"technique":[5,81,142],"to":[6,115,130],"learn":[7,117],"the":[8,24,30,33,37,44,54,60,64,70,121,124,136,144,147,162,165,179],"control":[9,177],"policy":[10,134],"for":[11,82,135],"an":[12,132,168],"agent":[13,25,45],"that":[14,53,85,158,171,199],"interacts":[15],"with":[16],"stochastic":[18],"environment.":[19],"In":[20,73],"any":[21],"given":[22],"state,":[23],"takes":[26],"some":[27,46],"action,":[28],"and":[29,106,197],"environment":[31,55,122],"determines":[32],"probability":[34,61],"distribution":[35,62],"over":[36,63],"next":[38,65],"state":[39,66],"as":[40,42,98,126,128],"well":[41,127],"gives":[43],"reward.":[47],"Most":[48],"RL":[49,80,110],"algorithms":[50],"typically":[51,113],"assume":[52],"satisfies":[56],"Markov":[57],"assumptions":[58],"(i.e.":[59],"depends":[67],"only":[68],"on":[69,188,207],"current":[71],"state).":[72],"this":[74],"paper,":[75],"we":[76,159,183],"propose":[77,140],"model-based":[79],"system":[84,148],"has":[86],"non-Markovian":[87],"dynamics.":[88,108],"Such":[89],"environments":[90],"are":[91],"common":[92],"in":[93,99,164],"many":[94],"real-world":[95,208],"applications":[96],"such":[97],"human":[100,193],"physiology,":[101],"biological":[102],"systems,":[103],"material":[104],"science,":[105],"population":[107],"Model-based":[109],"(MBRL)":[111],"techniques":[112],"try":[114,129],"simultaneously":[116],"model":[119,175,191],"of":[120,146,167,192],"from":[123,178],"data,":[125],"identify":[131],"optimal":[133,180],"learned":[137],"model.":[138],"We":[139,156],"where":[143],"non-Markovianity":[145],"modeled":[150],"through":[151],"fractional":[153,201],"dynamical":[154],"system.":[155],"show":[157,198],"can":[160,203],"quantify":[161],"difference":[163],"performance":[166],"MBRL":[169],"algorithm":[170],"uses":[172],"bounded":[173],"horizon":[174],"predictive":[176],"policy.":[181],"Finally,":[182],"demonstrate":[184],"our":[185,200],"proposed":[186],"framework":[187],"pharmacokinetic":[190],"blood":[194],"glucose":[195],"dynamics":[196],"models":[202],"capture":[204],"distant":[205],"correlations":[206],"datasets.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}