{"id":"https://openalex.org/W7204947799","doi":"https://doi.org/10.48550/arxiv.2608.28878","title":"Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management","display_name":"Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204947799","doi":"https://doi.org/10.48550/arxiv.2608.28878"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.28878","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28878","pdf_url":"https://arxiv.org/pdf/2608.28878","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/2608.28878","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125692463","display_name":"Yiming Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Yiming","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Northwestern University , Evanston , IL 60208 USA","Department of Electrical and Computer Engineering , University of Virginia , Charlottesville , VA 22904 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Northwestern University , Evanston , IL 60208 USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering , University of Virginia , Charlottesville , VA 22904 USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140347993","display_name":"Kun Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Kun","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Northwestern University , Evanston , IL 60208 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Northwestern University , Evanston , IL 60208 USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148891780","display_name":"Cong Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shen, Cong","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Northwestern University , Evanston , IL 60208 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Northwestern University , Evanston , IL 60208 USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081342685","display_name":"Dongning Guo","orcid":"https://orcid.org/0000-0001-9000-3480","observed_orcids":["https://orcid.org/0000-0001-9000-3480","https://orcid.org/0000-0002-5564-4319"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo, Dongning","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Northwestern University , Evanston , IL 60208 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Northwestern University , Evanston , IL 60208 USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11409","display_name":"Advanced Wireless Network Optimization","score":0.5903000235557556,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11409","display_name":"Advanced Wireless Network Optimization","score":0.5903000235557556,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.35839998722076416,"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/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.00800000037997961,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/decision-transformer","display_name":"decision transformer","score":0.8960000276565552},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9639999866485596},{"id":"https://openalex.org/keywords/wireless-resource-management","display_name":"wireless resource management","score":0.746999979019165},{"id":"https://openalex.org/keywords/coordinated-beamforming","display_name":"coordinated beamforming","score":0.9950000047683716},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"quality of service","score":0.8240000009536743},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"distributed learning","score":0.4189999997615814},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.4300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089999914169312},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6956999897956848},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5726000070571899},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4659999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41819998621940613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4153999984264374},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3822999894618988},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36629998683929443},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.28878","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28878","pdf_url":"https://arxiv.org/pdf/2608.28878","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.2608.28878","doi":"https://doi.org/10.48550/arxiv.2608.28878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28878","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:2608.28878","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28878","pdf_url":"https://arxiv.org/pdf/2608.28878","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":[{"score":0.428600013256073,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G7170043270","display_name":"SII-Center: SpectrumX \u2013 An NSF Spectrum Innovation Center","funder_award_id":"2132700","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8518852393","display_name":"Spectrum Access Rights, Operator Identification, and Consensus-Based Sharing Platform","funder_award_id":"2434044","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8901546329","display_name":"Institute for Data, Econometrics, Algorithms and Learning (IDEAL)","funder_award_id":"2216970","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204947799.pdf","grobid_xml":"https://content.openalex.org/works/W7204947799.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4408355143","https://openalex.org/W3005761304","https://openalex.org/W4413318807","https://openalex.org/W4396817492","https://openalex.org/W7217841386","https://openalex.org/W7206204335","https://openalex.org/W3091934141","https://openalex.org/W4281708619","https://openalex.org/W2950676878","https://openalex.org/W4416690336"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3,31,42,70,151],"hybrid":[4,43],"offline-online":[5],"multi-agent":[6,63],"reinforcement":[7],"learning":[8],"framework":[9,66],"based":[10],"on":[11,73,90,134],"decision":[12],"transformers.":[13],"The":[14,79],"policy":[15],"is":[16,37,81,139],"first":[17],"pretrained":[18,133],"offline":[19,54,146],"via":[20],"supervised":[21],"sequence":[22],"modeling":[23],"of":[24],"trajectories":[25],"generated":[26],"by":[27],"existing":[28],"policies,":[29],"providing":[30],"safe":[32],"and":[33,61,76,86,93,111,114],"sample-efficient":[34],"initialization.":[35],"It":[36],"then":[38],"fine-tuned":[39],"online":[40,137],"using":[41],"objective":[44],"that":[45,119],"incorporates":[46,67],"critic-guided":[47],"gradients,":[48],"enabling":[49],"performance":[50,126],"improvements":[51],"beyond":[52],"the":[53,65,120,144],"policy.":[55,147],"To":[56],"facilitate":[57],"stable":[58],"offline-to-online":[59],"transfer":[60],"effective":[62],"coordination,":[64],"return-weighted":[68],"sampling,":[69],"critic":[71],"conditioned":[72],"neighbors'":[74],"actions,":[75],"neighborhood-correlated":[77],"exploration.":[78],"approach":[80],"fully":[82],"distributed:":[83],"both":[84],"training":[85],"execution":[87],"rely":[88],"only":[89],"local":[91],"observations":[92],"limited":[94],"information":[95],"exchange":[96],"among":[97],"neighboring":[98],"agents.":[99],"Evaluations":[100],"with":[101],"dynamic":[102],"traffic":[103],"arrivals":[104],"in":[105],"two":[106],"settings:":[107],"(i)":[108],"joint":[109],"scheduling":[110],"power":[112],"allocation":[113],"(ii)":[115],"coordinated":[116],"beamforming,":[117],"show":[118],"proposed":[121],"method":[122],"achieves":[123],"quality-of-service":[124],"(QoS)":[125],"comparable":[127],"to":[128,142],"centralized":[129],"methods.":[130],"Moreover,":[131],"when":[132],"lower-quality":[135],"datasets,":[136],"fine-tuning":[138],"also":[140],"observed":[141],"surpass":[143],"initial":[145],"These":[148],"results":[149],"demonstrate":[150],"promising":[152],"learning-based":[153],"alternative":[154],"for":[155],"wireless":[156],"resource":[157],"management.":[158]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-09-02T00:00:00"}