{"id":"https://openalex.org/W4313648272","doi":"https://doi.org/10.1145/3579342.3579346","title":"A Unified Lyapunov Framework for Finite-Sample Analysis of Reinforcement Learning Algorithms","display_name":"A Unified Lyapunov Framework for Finite-Sample Analysis of Reinforcement Learning Algorithms","publication_year":2022,"publication_date":"2022-12-30","ids":{"openalex":"https://openalex.org/W4313648272","doi":"https://doi.org/10.1145/3579342.3579346"},"language":"en","primary_location":{"id":"doi:10.1145/3579342.3579346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579342.3579346","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-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/A5058269077","display_name":"Zaiwei Chen","orcid":"https://orcid.org/0000-0001-9915-5595"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zaiwei Chen","raw_affiliation_strings":["Caltech CMS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Caltech CMS","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058269077"],"corresponding_institution_ids":["https://openalex.org/I122411786"],"apc_list":null,"apc_paid":null,"fwci":0.1387,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57493192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"50","issue":"3","first_page":"12","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9927999973297119,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9915000200271606,"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":0.8149647116661072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6515443325042725},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5909919738769531},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5027852058410645},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47022032737731934},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.46357303857803345},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4424290060997009},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4293648898601532},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42711061239242554},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.4193030893802643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37808746099472046},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29932576417922974},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2758014500141144},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.17283222079277039},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.1321507692337036},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.09561622142791748}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8149647116661072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6515443325042725},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5909919738769531},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5027852058410645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47022032737731934},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.46357303857803345},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4424290060997009},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4293648898601532},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42711061239242554},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.4193030893802643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37808746099472046},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29932576417922974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2758014500141144},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.17283222079277039},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.1321507692337036},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.09561622142791748},{"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/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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":2,"locations":[{"id":"doi:10.1145/3579342.3579346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579342.3579346","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"},{"id":"pmh:oai:smartech.gatech.edu:1853/66568","is_oa":false,"landing_page_url":"http://repository.gatech.edu/bitstreams/224cfe46-7014-41ed-85dd-2d82a393d62d/download","pdf_url":null,"source":{"id":"https://openalex.org/S4377196313","display_name":"SMARTech Repository (Georgia Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130701444","host_organization_name":"Georgia Institute of Technology","host_organization_lineage":["https://openalex.org/I130701444"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2257979135","https://openalex.org/W2786036274","https://openalex.org/W2913932550","https://openalex.org/W3094472530","https://openalex.org/W3127825666","https://openalex.org/W3131821770","https://openalex.org/W3164660575","https://openalex.org/W3176355038","https://openalex.org/W4213377513","https://openalex.org/W4214535770","https://openalex.org/W4229028729","https://openalex.org/W4297329999","https://openalex.org/W4313648272"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W2473364827","https://openalex.org/W2134042548","https://openalex.org/W2772472730","https://openalex.org/W2964123095","https://openalex.org/W2607053317","https://openalex.org/W4306703873","https://openalex.org/W395196838"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3,24,105],"a":[4,28,114,123,129],"paradigm":[5],"where":[6,54,126],"an":[7,212],"agent":[8],"learns":[9],"to":[10,19,31,71,107,144,179],"accomplish":[11],"tasks":[12],"by":[13,37],"interacting":[14],"with":[15],"the":[16,38,52,72,84,97,100,108,134,153,160,171,184,189,193,200,215],"environment,":[17],"similar":[18],"how":[20],"humans":[21],"learn.":[22],"RL":[23,44,76,85,150,185],"therefore":[25],"viewed":[26],"as":[27,35,188],"promising":[29],"approach":[30,125],"achieve":[32],"artificial":[33],"intelligence,":[34],"evidenced":[36],"remarkable":[39],"empirical":[40],"successes.":[41],"However,":[42],"many":[43],"algorithms":[45,77,86,92,151],"are":[46,60,87],"theoretically":[47],"not":[48],"well-understood,":[49],"especially":[50],"in":[51,152,174,183,196],"setting":[53,155],"function":[55,132,165],"approximation":[56,90,166],"and":[57,117,162,199],"off-policy":[58,197,203],"sampling":[59],"employed.":[61],"My":[62],"thesis":[63,104],"[1]":[64],"aims":[65],"at":[66],"developing":[67],"thorough":[68],"theoretical":[69,177],"understanding":[70],"performance":[73],"of":[74,83,96,103,110,148,159,170,191,202,208,214,217],"various":[75,149],"through":[78],"finite-sample":[79,146],"analysis.":[80],"Since":[81],"most":[82],"essentially":[88],"stochastic":[89],"(SA)":[91],"for":[93],"solving":[94],"variants":[95],"Bellman":[98],"equation,":[99],"first":[101],"part":[102],"dedicated":[106],"analysis":[109],"general":[111],"SA":[112,141],"involving":[113],"contraction":[115],"operator,":[116],"under":[118],"Markovian":[119],"noise.":[120],"We":[121],"develop":[122],"Lyapunov":[124,131],"we":[127],"construct":[128],"novel":[130],"called":[133],"generaled":[135],"Moreau":[136],"envelope.":[137],"The":[138,205],"results":[139],"on":[140],"enable":[142],"us":[143],"establish":[145],"bounds":[147],"tabular":[154],"(cf.":[156,167],"Part":[157,168],"II":[158],"thesis)":[161],"when":[163],"using":[164],"III":[169],"thesis),":[172],"which":[173],"turn":[175],"provide":[176],"insights":[178],"several":[180],"important":[181],"problems":[182],"community,":[186],"such":[187],"efficiency":[190],"bootstrapping,":[192],"bias-variance":[194],"trade-off":[195],"learning,":[198],"stability":[201],"control.":[204],"main":[206],"body":[207],"this":[209],"document":[210],"provides":[211],"overview":[213],"contributions":[216],"my":[218],"thesis.":[219]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}