{"id":"https://openalex.org/W4414359257","doi":"https://doi.org/10.24963/ijcai.2025/634","title":"A Primal-dual Perspective for Distributed TD-learning","display_name":"A Primal-dual Perspective for Distributed TD-learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359257","doi":"https://doi.org/10.24963/ijcai.2025/634"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/634","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081465224","display_name":"Hanjin Lim","orcid":"https://orcid.org/0000-0003-4171-6622"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Han Dong Lim","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100654317","display_name":"Donghwan Lee","orcid":"https://orcid.org/0000-0002-4962-8478"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Donghwan Lee","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5698","last_page":"5706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.48010000586509705,"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/T10320","display_name":"Neural Networks and Applications","score":0.48010000586509705,"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/ode","display_name":"Ode","score":0.7196999788284302},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.625},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5591999888420105},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.46070000529289246},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.45320001244544983},{"id":"https://openalex.org/keywords/ordinary-differential-equation","display_name":"Ordinary differential equation","score":0.4090999960899353},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.391400009393692},{"id":"https://openalex.org/keywords/exponential-distribution","display_name":"Exponential distribution","score":0.38659998774528503}],"concepts":[{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.7196999788284302},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.625},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5170999765396118},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4593999981880188},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45680001378059387},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C51544822","wikidata":"https://www.wikidata.org/wiki/Q465274","display_name":"Ordinary differential equation","level":3,"score":0.4090999960899353},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C55350006","wikidata":"https://www.wikidata.org/wiki/Q237193","display_name":"Exponential distribution","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.34130001068115234},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C112714845","wikidata":"https://www.wikidata.org/wiki/Q1482001","display_name":"Distributed parameter system","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C2779086853","wikidata":"https://www.wikidata.org/wiki/Q5283157","display_name":"Distributed knowledge","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/634","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,20],"goal":[1],"of":[2,50,63],"this":[3],"paper":[4],"is":[5,23,103],"to":[6,41,56],"investigate":[7],"distributed":[8,26,69],"temporal":[9],"difference":[10],"(TD)":[11],"learning":[12],"for":[13],"a":[14,106],"networked":[15],"multi-agent":[16],"Markov":[17],"decision":[18],"process.":[19],"proposed":[21,90],"approach":[22],"based":[24],"on":[25,45],"optimization":[27],"algorithms,":[28],"which":[29],"can":[30],"be":[31],"interpreted":[32],"as":[33],"primal-dual":[34,52],"ordinary":[35],"differential":[36],"equation":[37],"(ODE)":[38],"dynamics":[39,54],"subject":[40,55],"null-space":[42,57],"constraints.":[43],"Based":[44],"the":[46,51,61,64,89,95,98],"exponential":[47],"convergence":[48],"behavior":[49,62],"ODE":[53],"constraints,":[58],"we":[59],"examine":[60],"final":[65],"iterate":[66],"in":[67],"various":[68],"TD-learning":[70],"scenarios,":[71],"considering":[72],"both":[73,80],"constant":[74],"and":[75,78,82],"diminishing":[76],"step-sizes":[77],"incorporating":[79],"i.i.d.":[81],"Markovian":[83],"observation":[84],"models.":[85],"Unlike":[86],"existing":[87],"methods,":[88],"algorithm":[91],"does":[92],"not":[93],"require":[94],"assumption":[96],"that":[97],"underlying":[99],"communication":[100],"network":[101],"structure":[102],"characterized":[104],"by":[105],"doubly":[107],"stochastic":[108],"matrix.":[109]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}