{"id":"https://openalex.org/W4414571797","doi":"https://doi.org/10.1007/s11633-025-1550-8","title":"Enhancing Federated Reinforcement Learning: A Consensus-based Approach for Both Homogeneous and Heterogeneous Agents","display_name":"Enhancing Federated Reinforcement Learning: A Consensus-based Approach for Both Homogeneous and Heterogeneous Agents","publication_year":2025,"publication_date":"2025-09-27","ids":{"openalex":"https://openalex.org/W4414571797","doi":"https://doi.org/10.1007/s11633-025-1550-8"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-025-1550-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-025-1550-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-025-1550-8.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11633-025-1550-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009770666","display_name":"Alessandro Giuseppi","orcid":"https://orcid.org/0000-0001-5503-8506"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessandro Giuseppi","raw_affiliation_strings":["Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, 00185, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, 00185, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018146563","display_name":"Danilo Menegatti","orcid":"https://orcid.org/0000-0001-9090-0050"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Menegatti","raw_affiliation_strings":["Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, 00185, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, 00185, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088978718","display_name":"Antonio Pietrabissa","orcid":"https://orcid.org/0000-0003-0188-3346"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Pietrabissa","raw_affiliation_strings":["Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, 00185, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, 00185, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009770666"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1414586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"5","first_page":"929","last_page":"940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9951000213623047,"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":0.9951000213623047,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11942","display_name":"Transportation and Mobility Innovations","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8398000001907349},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.5781000256538391},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4984000027179718},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4713999927043915},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.44359999895095825},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4138999879360199},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.361299991607666},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.34880000352859497}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8398000001907349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131999731063843},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6509000062942505},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.5781000256538391},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C10558101","wikidata":"https://www.wikidata.org/wiki/Q689855","display_name":"Smart grid","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11633-025-1550-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-025-1550-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-025-1550-8.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1752379","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1752379","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s11633-025-1550-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-025-1550-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-025-1550-8.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322510","display_name":"Sapienza Universit\u00e0 di Roma","ror":"https://ror.org/02be6w209"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414571797.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1583837637","https://openalex.org/W1658008008","https://openalex.org/W2017957151","https://openalex.org/W2099618002","https://openalex.org/W2107396783","https://openalex.org/W2113561163","https://openalex.org/W2277615321","https://openalex.org/W2602856279","https://openalex.org/W2604738573","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2913756371","https://openalex.org/W2914304175","https://openalex.org/W2914584698","https://openalex.org/W2982409974","https://openalex.org/W3005294098","https://openalex.org/W3094736543","https://openalex.org/W3099980742","https://openalex.org/W3129875850","https://openalex.org/W3130426370","https://openalex.org/W3161868942","https://openalex.org/W3165469371","https://openalex.org/W3205598877","https://openalex.org/W4214717370","https://openalex.org/W4241811150","https://openalex.org/W4285189244","https://openalex.org/W4288685354","https://openalex.org/W4289365086","https://openalex.org/W4298857966","https://openalex.org/W4312813448","https://openalex.org/W4312985618","https://openalex.org/W4363649062","https://openalex.org/W4382935738","https://openalex.org/W4388145514"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Federated":[1],"reinforcement":[2,27],"learning":[3,28],"(FedRL)":[4],"is":[5,51,150],"an":[6],"emerging":[7],"paradigm":[8],"in":[9,110,133],"data-driven":[10],"control":[11,22],"where":[12],"a":[13,25,48,67,71,129,134,138],"group":[14],"of":[15,33,37,128],"decision-making":[16],"agents":[17,112],"cooperate":[18],"to":[19,69],"learn":[20],"optimal":[21],"laws":[23],"through":[24],"distributed":[26,56],"procedure,":[29],"with":[30,92,107],"the":[31,35,44,55,102,153],"peculiarity":[32],"having":[34],"constraints":[36],"not":[38],"sharing":[39],"any":[40],"process/control":[41],"data.":[42],"In":[43],"typical":[45],"FedRL":[46],"setting,":[47],"centralized":[49],"entity":[50],"responsible":[52],"for":[53,152],"orchestrating":[54],"training":[57],"process.":[58],"To":[59],"remove":[60],"this":[61,64],"design":[62],"limitation,":[63],"work":[65],"proposes":[66],"solution":[68],"enable":[70],"fully":[72],"decentralized":[73],"approach":[74],"leveraging":[75],"on":[76,124],"results":[77],"from":[78],"consensus":[79],"theory.":[80],"The":[81,119],"proposed":[82,120],"algorithm,":[83],"named":[84],"FedRLCon,":[85],"can":[86,96],"then":[87],"deal":[88],"with:":[89],"1)":[90],"scenarios":[91,106],"homogeneous":[93],"agents,":[94,109],"which":[95,111],"share":[97,114],"their":[98,115],"actor":[99],"and,":[100],"possibly,":[101],"critic":[103,116],"networks;":[104],"2)":[105],"heterogeneous":[108],"may":[113],"network":[117,136],"only.":[118],"algorithms":[121],"are":[122],"validated":[123],"two":[125],"scenarios,":[126],"consisting":[127],"resource":[130],"management":[131],"problem":[132],"communication":[135],"and":[137],"smart":[139],"grid":[140],"case":[141],"study.":[142],"Our":[143],"tests":[144],"show":[145],"that":[146],"practically":[147],"no":[148],"performance":[149],"lost":[151],"decentralization.":[154]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}