{"id":"https://openalex.org/W4397028151","doi":"https://doi.org/10.48550/arxiv.2405.09660","title":"Fast Two-Time-Scale Stochastic Gradient Method with Applications in Reinforcement Learning","display_name":"Fast Two-Time-Scale Stochastic Gradient Method with Applications in Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-15","ids":{"openalex":"https://openalex.org/W4397028151","doi":"https://doi.org/10.48550/arxiv.2405.09660"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.09660","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.09660","pdf_url":"https://arxiv.org/pdf/2405.09660","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.09660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069872754","display_name":"Sihan Zeng","orcid":"https://orcid.org/0000-0002-0061-5780","observed_orcids":["https://orcid.org/0000-0002-0061-5780"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeng, Sihan","raw_affiliation_strings":["Research UT Austin , Department of Aerospace Engineering & Engineering Mechanics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research UT Austin , Department of Aerospace Engineering & Engineering Mechanics","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035207859","display_name":"Thinh T. Doan","orcid":"https://orcid.org/0000-0001-5135-3429","observed_orcids":["https://orcid.org/0000-0001-5135-3429"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doan, Thinh T.","raw_affiliation_strings":["Research UT Austin , Department of Aerospace Engineering & Engineering Mechanics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research UT Austin , Department of Aerospace Engineering & Engineering Mechanics","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5698000192642212,"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":0.5698000192642212,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.3991999924182892,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.011500000022351742,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stochastic-gradient-methods","display_name":"stochastic gradient algorithm","score":0.765999972820282},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6060000061988831},{"id":"https://openalex.org/keywords/policy-evaluation","display_name":"policy evaluation","score":0.8799999952316284},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.9710000157356262},{"id":"https://openalex.org/keywords/polyak-lojasiewicz-condition","display_name":"Polyak-Lojasiewicz condition","score":0.9459999799728394},{"id":"https://openalex.org/keywords/strongly-monotone-operators","display_name":"strongly monotone operators","score":0.6990000009536743},{"id":"https://openalex.org/keywords/bi-level-optimization","display_name":"bi-level optimization","score":0.7160000205039978}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7489328384399414},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6625434160232544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5386360287666321},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4446549713611603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34134534001350403},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13549736142158508},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08691880106925964},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06849586963653564},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2405.09660","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.09660","pdf_url":"https://arxiv.org/pdf/2405.09660","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.09660","doi":"https://doi.org/10.48550/arxiv.2405.09660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.09660","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.09660","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.09660","pdf_url":"https://arxiv.org/pdf/2405.09660","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2248262269","display_name":"CAREER: Foundations of Scalable and Resilient Distributed Real-Time Decision Making in Open Multi-Agent Systems","funder_award_id":"2339509","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7238386145","display_name":"Collaborative Research: CIF: Small: Mathematical and Algorithmic Foundations of Multi-Task Learning","funder_award_id":"2343599","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/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4397028151.pdf","grobid_xml":"https://content.openalex.org/works/W4397028151.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4381713631"],"related_works":["https://openalex.org/W4392587904","https://openalex.org/W2996964934","https://openalex.org/W2967034031","https://openalex.org/W4391244259","https://openalex.org/W2795561155","https://openalex.org/W2602600938","https://openalex.org/W4413855694","https://openalex.org/W4403663261","https://openalex.org/W7163010757","https://openalex.org/W4416013634"],"abstract_inverted_index":{"Two-time-scale":[0],"optimization":[1,20,29,39,80],"is":[2,59,96],"a":[3,13,31,54,65,74],"framework":[4,40],"introduced":[5],"in":[6,22,109,221],"Zeng":[7],"et":[8],"al.":[9],"(2024)":[10],"that":[11,81,199],"abstracts":[12],"range":[14],"of":[15,34,53,64,93,106,139,148,155,176,205,209],"policy":[16,19],"evaluation":[17,48],"and":[18,112,165],"problems":[21],"reinforcement":[23],"learning":[24],"(RL).":[25],"Akin":[26],"to":[27,60,97,102,118,185,194],"bi-level":[28],"under":[30,152],"particular":[32],"type":[33],"stochastic":[35,180],"oracle,":[36],"the":[37,51,62,87,104,107,120,128,132,136,144,149,156,173,177,190,203,206,210],"two-time-scale":[38,79,179],"has":[41],"an":[42,99],"upper":[43,113],"level":[44,56],"objective":[45,158],"whose":[46],"gradient":[47],"depends":[49],"on":[50],"solution":[52],"lower":[55,111],"problem,":[57],"which":[58],"find":[61],"root":[63],"strongly":[66],"monotone":[67],"operator.":[68],"In":[69],"this":[70],"work,":[71],"we":[72,187,213],"propose":[73],"new":[75],"method":[76],"for":[77],"solving":[78],"achieves":[82],"significantly":[83,170],"faster":[84],"convergence":[85,146],"than":[86],"prior":[88],"arts.":[89],"The":[90],"key":[91],"idea":[92],"our":[94,140,215],"approach":[95],"leverage":[98],"averaging":[100,125],"step":[101],"improve":[103,171],"estimates":[105],"operators":[108],"both":[110],"levels":[114],"before":[115],"using":[116],"them":[117],"update":[119],"decision":[121],"variables.":[122],"These":[123,168],"additional":[124],"steps":[126],"eliminate":[127],"direct":[129],"coupling":[130],"between":[131],"main":[133],"variables,":[134],"enabling":[135],"accelerated":[137],"performance":[138,204],"algorithm.":[141,182],"We":[142],"characterize":[143],"finite-time":[145],"rates":[147,169],"proposed":[150,191],"algorithm":[151,192],"various":[153],"conditions":[154],"underlying":[157],"function,":[159],"including":[160],"strong":[161],"convexity,":[162],"Polyak-Lojasiewicz":[163],"condition,":[164],"general":[166],"non-convexity.":[167],"over":[172],"best-known":[174],"complexity":[175],"standard":[178],"approximation":[181],"When":[183],"applied":[184],"RL,":[186],"show":[188],"how":[189],"specializes":[193],"novel":[195],"online":[196],"sample-based":[197],"methods":[198],"surpass":[200],"or":[201],"match":[202],"existing":[207],"state":[208],"art.":[211],"Finally,":[212],"support":[214],"theoretical":[216],"results":[217],"with":[218],"numerical":[219],"simulations":[220],"RL.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-05-18T00:00:00"}