{"id":"https://openalex.org/W7123360326","doi":"https://doi.org/10.1109/cdc57313.2025.11312385","title":"PrELIN: Provably Efficient Local-Information Networked Multi-Agent Reinforcement Learning","display_name":"PrELIN: Provably Efficient Local-Information Networked Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123360326","doi":"https://doi.org/10.1109/cdc57313.2025.11312385"},"language":"en","primary_location":{"id":"doi:10.1109/cdc57313.2025.11312385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure-oai.bham.ac.uk/ws/files/274213230/Sample_complexity_analysis_for_PrELIN_final.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122866371","display_name":"Ziyue Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I3133184724","display_name":"University College Birmingham","ror":"https://ror.org/042ver755","country_code":"GB","type":"education","lineage":["https://openalex.org/I3133184724"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ziyue Chu","raw_affiliation_strings":["University of Birmingham,School of Computer Science, College of Engineering and Physical Sciences,Birmingham,United Kingdom,B15 2TT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham,School of Computer Science, College of Engineering and Physical Sciences,Birmingham,United Kingdom,B15 2TT","institution_ids":["https://openalex.org/I79619799","https://openalex.org/I3133184724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025595195","display_name":"Sharu Theresa Jose","orcid":"https://orcid.org/0000-0001-8872-3462"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]},{"id":"https://openalex.org/I3133184724","display_name":"University College Birmingham","ror":"https://ror.org/042ver755","country_code":"GB","type":"education","lineage":["https://openalex.org/I3133184724"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sharu Theresa Jose","raw_affiliation_strings":["University of Birmingham,School of Computer Science, College of Engineering and Physical Sciences,Birmingham,United Kingdom,B15 2TT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham,School of Computer Science, College of Engineering and Physical Sciences,Birmingham,United Kingdom,B15 2TT","institution_ids":["https://openalex.org/I79619799","https://openalex.org/I3133184724"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038355992","display_name":"Leonardo Stella","orcid":"https://orcid.org/0000-0002-2670-9873"},"institutions":[{"id":"https://openalex.org/I3133184724","display_name":"University College Birmingham","ror":"https://ror.org/042ver755","country_code":"GB","type":"education","lineage":["https://openalex.org/I3133184724"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leonardo Stella","raw_affiliation_strings":["University of Birmingham,School of Computer Science, College of Engineering and Physical Sciences,Birmingham,United Kingdom,B15 2TT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham,School of Computer Science, College of Engineering and Physical Sciences,Birmingham,United Kingdom,B15 2TT","institution_ids":["https://openalex.org/I79619799","https://openalex.org/I3133184724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5122866371"],"corresponding_institution_ids":["https://openalex.org/I3133184724","https://openalex.org/I79619799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80206042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6077","last_page":"6082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.28459998965263367,"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":0.28459998965263367,"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":0.2784999907016754,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0722000002861023,"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":0.8704000115394592},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6990000009536743},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5720000267028809},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5157999992370605},{"id":"https://openalex.org/keywords/information-exchange","display_name":"Information exchange","score":0.4666000008583069},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.3919999897480011}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8704000115394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285000085830688},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5720000267028809},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.427700012922287},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40310001373291016},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3752000033855438},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2978000044822693},{"id":"https://openalex.org/C179145077","wikidata":"https://www.wikidata.org/wiki/Q5154130","display_name":"Communication complexity","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.2637999951839447}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/44ed414e-ac72-451a-8aed-05dad3c6f49b","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/44ed414e-ac72-451a-8aed-05dad3c6f49b","pdf_url":"https://pure-oai.bham.ac.uk/ws/files/274213230/Sample_complexity_analysis_for_PrELIN_final.pdf","source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chu, Z, Jose, S T & Stella, L 2026, PrELIN : Provably Efficient Local-Information Networked Multi-Agent Reinforcement Learning. in 2025 IEEE 64th Conference on Decision and Control (CDC). Proceedings of the IEEE Conference on Decision & Control , IEEE, pp. 6077-6082, 2025 IEEE 64th Conference on Decision and Control, Rio de Janeiro, Brazil, 10/12/25. https://doi.org/10.1109/CDC57313.2025.11312385","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/44ed414e-ac72-451a-8aed-05dad3c6f49b","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/44ed414e-ac72-451a-8aed-05dad3c6f49b","pdf_url":"https://pure-oai.bham.ac.uk/ws/files/274213230/Sample_complexity_analysis_for_PrELIN_final.pdf","source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chu, Z, Jose, S T & Stella, L 2026, PrELIN : Provably Efficient Local-Information Networked Multi-Agent Reinforcement Learning. in 2025 IEEE 64th Conference on Decision and Control (CDC). Proceedings of the IEEE Conference on Decision & Control , IEEE, pp. 6077-6082, 2025 IEEE 64th Conference on Decision and Control, Rio de Janeiro, Brazil, 10/12/25. https://doi.org/10.1109/CDC57313.2025.11312385","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7123360326.pdf","grobid_xml":"https://content.openalex.org/works/W7123360326.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"a":[4,48,60,76,97,120],"surge":[5],"of":[6,21,35,91],"interest":[7],"in":[8,17,42],"decentralized":[9],"learning":[10,29],"approaches":[11,25,83],"to":[12],"tackle":[13],"complex":[14],"collaborative":[15],"tasks":[16],"multi-agent":[18,27],"systems.":[19],"One":[20],"the":[22,33,39,67,89,92,109,150,154,159,170],"most":[23],"promising":[24],"is":[26,102],"reinforcement":[28],"(MARL).":[30],"Yet,":[31],"as":[32],"number":[34],"agents":[36],"becomes":[37],"larger,":[38],"sample":[40,162],"complexity":[41,163],"MARL":[43,52,123],"increases":[44],"exponentially,":[45],"making":[46],"scalability":[47],"fundamental":[49],"issue.":[50],"Networked":[51],"algorithms":[53],"can":[54],"address":[55],"this":[56,112,116],"issue":[57],"by":[58,118],"leveraging":[59],"communication":[61,93],"network":[62,71],"for":[63,164],"information":[64,145],"exchange":[65],"between":[66,153],"agents.":[68,155],"For":[69],"homogeneous":[70],"MARL,":[72,138],"previous":[73],"research":[74],"established":[75],"regret":[77,160,171],"upper-bound":[78],"$\\sqrt":[79],"{M{H^4}SAT}":[80],"$.":[81],"Recent":[82],"rely":[84],"on":[85,108,149],"global":[86,144],"knowledge":[87],"about":[88],"structure":[90],"network,":[94],"which":[95],"poses":[96],"serious":[98],"limitation":[99,117],"when":[100],"it":[101],"not":[103,141],"known":[104],"or":[105],"changes":[106],"depending":[107],"task.":[110],"In":[111],"paper,":[113],"we":[114,157],"overcome":[115],"proposing":[119],"novel":[121],"networked":[122,136],"algorithm":[124,166],"with":[125],"an":[126],"upper-confidence":[127],"bound":[128,172],"(UCB)":[129],"exploration":[130],"strategy,":[131],"called":[132],"provably":[133],"efficient":[134],"local-information":[135],"(PrELIN)":[137],"that":[139,169],"does":[140],"require":[142],"any":[143],"but":[146],"only":[147],"relies":[148],"local":[151],"interactions":[152],"Furthermore,":[156],"derive":[158],"and":[161,167],"our":[165],"show":[168],"may":[173],"still":[174],"remain":[175],"sublinear.":[176]},"counts_by_year":[],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2026-01-14T00:00:00"}