{"id":"https://openalex.org/W4414648028","doi":"https://doi.org/10.1109/vtc2025-spring65109.2025.11174624","title":"Asynchronous Multi-Agent Reinforcement Learning for Scheduling in Subnetworks","display_name":"Asynchronous Multi-Agent Reinforcement Learning for Scheduling in Subnetworks","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4414648028","doi":"https://doi.org/10.1109/vtc2025-spring65109.2025.11174624"},"language":"en","primary_location":{"id":"doi:10.1109/vtc2025-spring65109.2025.11174624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vtc2025-spring65109.2025.11174624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 101st Vehicular Technology Conference (VTC2025-Spring)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/8a786562-eb36-4675-b518-9a7b76ea5f1c","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014134632","display_name":"Ashvin Srinivasan","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ashvin Srinivasan","raw_affiliation_strings":["Aalto University,Department of Information and Communications Engineering,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027033026","display_name":"Junshan Zhang","orcid":"https://orcid.org/0000-0002-3840-1753"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junshan Zhang","raw_affiliation_strings":["College of Engineering,University of California, Davis,California,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering,University of California, Davis,California,USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006597250","display_name":"Olav Tirkkonen","orcid":"https://orcid.org/0000-0002-2611-1636"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Olav Tirkkonen","raw_affiliation_strings":["Aalto University,Department of Information and Communications Engineering,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9190000295639038,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9190000295639038,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/subnetwork","display_name":"Subnetwork","score":0.7865999937057495},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7601000070571899},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7059000134468079},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6881999969482422},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6793000102043152},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6047999858856201},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.40389999747276306},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37940001487731934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439000248908997},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.7865999937057495},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7601000070571899},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7059000134468079},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6881999969482422},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6069999933242798},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6047999858856201},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.40389999747276306},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36800000071525574},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.3522999882698059},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.33799999952316284},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.3231000006198883},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.32179999351501465},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C68649174","wikidata":"https://www.wikidata.org/wiki/Q1379116","display_name":"Base station","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/vtc2025-spring65109.2025.11174624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vtc2025-spring65109.2025.11174624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 101st Vehicular Technology Conference (VTC2025-Spring)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/140451","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/8a786562-eb36-4675-b518-9a7b76ea5f1c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/140451","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/8a786562-eb36-4675-b518-9a7b76ea5f1c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2890389408","https://openalex.org/W2962664652","https://openalex.org/W3155030480","https://openalex.org/W3162884489","https://openalex.org/W3210367321","https://openalex.org/W3216069328","https://openalex.org/W4212888567","https://openalex.org/W4281625469","https://openalex.org/W4313068113","https://openalex.org/W4376480739","https://openalex.org/W4385269823","https://openalex.org/W4406266987"],"related_works":[],"abstract_inverted_index":{"We":[0,113],"address":[1,77],"radio":[2],"resource":[3,159],"scheduling":[4,28,63],"in":[5],"a":[6,54,70,82,125],"network":[7],"of":[8,61,138],"multiple":[9],"in-X":[10],"subnetworks":[11],"providing":[12],"wireless":[13],"Ultra-Reliable":[14],"Low-Latency":[15],"Communication":[16],"(URLLC)":[17],"service.":[18],"Each":[19],"subnetwork":[20],"is":[21,67,122],"controlled":[22],"by":[23],"an":[24,115],"agent":[25,121],"responsible":[26],"for":[27,39],"resources":[29],"to":[30,58,106],"its":[31],"devices.":[32],"Agents":[33],"rely":[34],"solely":[35],"on":[36],"interference":[37],"measurements":[38],"information":[40],"about":[41],"other":[42],"agents,":[43],"with":[44,98],"no":[45],"explicit":[46],"coordination.":[47],"Subnetwork":[48],"mobility":[49],"and":[50,109,134,153,161],"fast-fading":[51],"effects":[52],"create":[53],"non-stationary":[55],"environment,":[56],"adding":[57],"the":[59,62,78,99,136,139,146],"complexity":[60],"problem.":[64],"This":[65,127],"scenario":[66],"modeled":[68],"as":[69],"multi-agent":[71],"Markov":[72],"Decision":[73],"Process":[74],"(MDP).":[75],"To":[76],"problem,":[79],"we":[80],"propose":[81],"Multi-Agent":[83],"Deep":[84,100],"Reinforcement":[85],"Learning":[86],"(MADRL)":[87],"approach":[88],"under":[89],"URLLC":[90],"constraints,":[91],"which":[92],"integrates":[93],"Long":[94],"Short-Term":[95],"Memory":[96],"(LSTM)":[97],"Deterministic":[101],"Policy":[102],"Gradient":[103],"(DDPG)":[104],"algorithm":[105],"manage":[107],"non-stationarity":[108],"high-dimensional":[110],"action":[111],"spaces.":[112],"apply":[114],"asynchronous":[116,147],"update":[117,148],"strategy,":[118],"where":[119],"one":[120],"updating":[123],"at":[124],"time.":[126],"reduces":[128],"learning":[129],"variability,":[130],"resolves":[131],"policy":[132],"conflicts,":[133],"improves":[135],"interpretability":[137],"MADRL":[140],"approach.":[141],"Simulation":[142],"results":[143],"demonstrate":[144],"that":[145],"mechanism":[149],"outperforms":[150],"synchronous":[151],"updates":[152],"baseline":[154],"methods,":[155],"achieving":[156],"superior":[157],"reliability,":[158],"utilization,":[160],"explainability.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}