{"id":"https://openalex.org/W4404370995","doi":"https://doi.org/10.1109/tccn.2024.3499357","title":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","display_name":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404370995","doi":"https://doi.org/10.1109/tccn.2024.3499357"},"language":"en","primary_location":{"id":"doi:10.1109/tccn.2024.3499357","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tccn.2024.3499357","pdf_url":null,"source":{"id":"https://openalex.org/S2484188435","display_name":"IEEE Transactions on Cognitive Communications and Networking","issn_l":"2332-7731","issn":["2332-7731","2372-2045"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive Communications and Networking","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tccn.2024.3499357","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017608924","display_name":"Eslam Eldeeb","orcid":"https://orcid.org/0000-0002-6322-2036"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Eslam Eldeeb","raw_affiliation_strings":["Centre for Wireless Communications, University of Oulu, Oulu, Finland","Centre for Wireless Communications (CWC), University of Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-6322-2036","affiliations":[{"raw_affiliation_string":"Centre for Wireless Communications, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]},{"raw_affiliation_string":"Centre for Wireless Communications (CWC), University of Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032242918","display_name":"Houssem Sifaou","orcid":"https://orcid.org/0000-0003-0630-7073"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Houssem Sifaou","raw_affiliation_strings":["Department of Engineering, King's Communications, Learning and Information Processing Lab, Centre for Intelligent Information Processing Systems, King's College London, London, U.K","Department of Engineering, King’s Communications, Learning and Information Processing (KCLIP) lab, Centre for Intelligent Information Processing Systems (CIIPS), King’s College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0003-0630-7073","affiliations":[{"raw_affiliation_string":"Department of Engineering, King's Communications, Learning and Information Processing Lab, Centre for Intelligent Information Processing Systems, King's College London, London, U.K","institution_ids":["https://openalex.org/I183935753","https://openalex.org/I4210119896"]},{"raw_affiliation_string":"Department of Engineering, King’s Communications, Learning and Information Processing (KCLIP) lab, Centre for Intelligent Information Processing Systems (CIIPS), King’s College London, London, U.K","institution_ids":["https://openalex.org/I4210119896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017736224","display_name":"Osvaldo Simeone","orcid":"https://orcid.org/0000-0001-9898-3209"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Osvaldo Simeone","raw_affiliation_strings":["Department of Engineering, King's Communications, Learning and Information Processing Lab, Centre for Intelligent Information Processing Systems, King's College London, London, U.K","Department of Engineering, King’s Communications, Learning and Information Processing (KCLIP) lab, Centre for Intelligent Information Processing Systems (CIIPS), King’s College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9898-3209","affiliations":[{"raw_affiliation_string":"Department of Engineering, King's Communications, Learning and Information Processing Lab, Centre for Intelligent Information Processing Systems, King's College London, London, U.K","institution_ids":["https://openalex.org/I183935753","https://openalex.org/I4210119896"]},{"raw_affiliation_string":"Department of Engineering, King’s Communications, Learning and Information Processing (KCLIP) lab, Centre for Intelligent Information Processing Systems (CIIPS), King’s College London, London, U.K","institution_ids":["https://openalex.org/I4210119896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087038487","display_name":"Mohammad Shehab","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohammad Shehab","raw_affiliation_strings":["CEMSE Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","CEMSE Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-2391-3171","affiliations":[{"raw_affiliation_string":"CEMSE Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"CEMSE Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040878028","display_name":"Hirley Alves","orcid":"https://orcid.org/0000-0002-8689-5313"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Hirley Alves","raw_affiliation_strings":["Centre for Wireless Communications, University of Oulu, Oulu, Finland","Centre for Wireless Communications (CWC), University of Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-8689-5313","affiliations":[{"raw_affiliation_string":"Centre for Wireless Communications, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]},{"raw_affiliation_string":"Centre for Wireless Communications (CWC), University of Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9153,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87787484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"11","issue":"3","first_page":"1913","last_page":"1926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6955999732017517,"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":0.6955999732017517,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.6065000295639038,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.5882999897003174,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8138782382011414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8044592142105103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42894411087036133},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3857743442058563}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8138782382011414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044592142105103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42894411087036133},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3857743442058563}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tccn.2024.3499357","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tccn.2024.3499357","pdf_url":null,"source":{"id":"https://openalex.org/S2484188435","display_name":"IEEE Transactions on Cognitive Communications and Networking","issn_l":"2332-7731","issn":["2332-7731","2372-2045"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive Communications and Networking","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tccn.2024.3499357","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tccn.2024.3499357","pdf_url":null,"source":{"id":"https://openalex.org/S2484188435","display_name":"IEEE Transactions on Cognitive Communications and Networking","issn_l":"2332-7731","issn":["2332-7731","2372-2045"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive Communications and Networking","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1824793925","display_name":"6G Flagship - 6G-Enabled Wireless Smart Society & Ecosystem","funder_award_id":"346208","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G3079698552","display_name":"A holistic flagship towards the 6G network platform and system, to inspire digital transformation, for the world to act together in meeting needs in society and ecosystems with novel 6G services","funder_award_id":"101095759","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1647779468","https://openalex.org/W2765302304","https://openalex.org/W2768771208","https://openalex.org/W2898035736","https://openalex.org/W2955338161","https://openalex.org/W2963658727","https://openalex.org/W2969195240","https://openalex.org/W2969525674","https://openalex.org/W3002189898","https://openalex.org/W3005761304","https://openalex.org/W3007091509","https://openalex.org/W3010109240","https://openalex.org/W3084578038","https://openalex.org/W3122367457","https://openalex.org/W3129782062","https://openalex.org/W3156032009","https://openalex.org/W3197857544","https://openalex.org/W4237591687","https://openalex.org/W4284964448","https://openalex.org/W4288768987","https://openalex.org/W4312805548","https://openalex.org/W4322729780","https://openalex.org/W4379058658","https://openalex.org/W4386280791","https://openalex.org/W4387171915","https://openalex.org/W4388040576","https://openalex.org/W4389332150","https://openalex.org/W4396817492","https://openalex.org/W6638018090","https://openalex.org/W6683300800","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6751629939","https://openalex.org/W6776438516","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6789090588","https://openalex.org/W6796880758","https://openalex.org/W6799946856","https://openalex.org/W6804100093","https://openalex.org/W6810348208","https://openalex.org/W6840739175","https://openalex.org/W6851312059","https://openalex.org/W6852554612","https://openalex.org/W6855271737","https://openalex.org/W6857008120"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,48,132],"(RL)":[2],"has":[3],"been":[4],"widely":[5],"adopted":[6],"for":[7,28,43],"controlling":[8],"and":[9,105,115,130,150],"optimizing":[10],"complex":[11],"engineering":[12],"systems":[13],"such":[14],"as":[15,140],"next-generation":[16],"wireless":[17],"networks.":[18],"An":[19],"important":[20],"challenge":[21],"in":[22,40,158],"adopting":[23],"RL":[24,104],"is":[25,37,67,151],"the":[26,32,59,81,86,110,116,121,154],"need":[27],"direct":[29,70],"access":[30],"to":[31,80,108,139,153],"physical":[33],"environment.":[34],"This":[35],"limitation":[36],"particularly":[38],"severe":[39],"multi-agent":[41,46,141],"systems,":[42],"which":[44],"conventional":[45],"reinforcement":[47],"(MARL)":[49],"requires":[50],"a":[51,69],"large":[52],"number":[53],"of":[54,72,88,123],"coordinated":[55],"online":[56,73],"interactions":[57],"with":[58],"environment":[60],"during":[61,90],"training.":[62,91],"When":[63],"only":[64],"offline":[65,98,124],"data":[66],"available,":[68],"application":[71],"MARL":[74,99,136],"schemes":[75],"would":[76],"generally":[77],"fail":[78],"due":[79],"epistemic":[82,117],"uncertainty":[83,114,118],"entailed":[84],"by":[85],"lack":[87],"exploration":[89],"In":[92],"this":[93],"work,":[94],"we":[95],"propose":[96],"an":[97],"scheme":[100],"that":[101],"integrates":[102],"distributional":[103],"conservative":[106,142],"Q-learning":[107],"address":[109],"environment's":[111],"inherent":[112],"aleatoric":[113],"arising":[119],"from":[120],"use":[122],"data.":[125],"We":[126],"explore":[127],"both":[128],"independent":[129],"joint":[131],"strategies.":[133],"The":[134],"proposed":[135],"scheme,":[137],"referred":[138],"quantile":[143],"regression,":[144],"addresses":[145],"general":[146],"risk-sensitive":[147],"design":[148],"criteria":[149],"applied":[152],"trajectory":[155],"planning":[156],"problem":[157],"drone":[159],"networks,":[160],"showcasing":[161],"its":[162],"advantages.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}