{"id":"https://openalex.org/W4402835264","doi":"https://doi.org/10.1109/vtc2024-spring62846.2024.10683517","title":"Federated Multi-Agent Reinforcement Learning for Heterogeneous Action Spaces","display_name":"Federated Multi-Agent Reinforcement Learning for Heterogeneous Action Spaces","publication_year":2024,"publication_date":"2024-06-24","ids":{"openalex":"https://openalex.org/W4402835264","doi":"https://doi.org/10.1109/vtc2024-spring62846.2024.10683517"},"language":"en","primary_location":{"id":"doi:10.1109/vtc2024-spring62846.2024.10683517","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vtc2024-spring62846.2024.10683517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 99th Vehicular Technology Conference (VTC2024-Spring)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100784818","display_name":"Sheng Shen","orcid":"https://orcid.org/0000-0003-4734-1008"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Sheng Shen","raw_affiliation_strings":["School of Electrical and Computer Engineering, The University of Sydney,Darlington,NSW,2008"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, The University of Sydney,Darlington,NSW,2008","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068478144","display_name":"Teng Joon Lim","orcid":"https://orcid.org/0000-0002-3356-2240"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Teng Joon Lim","raw_affiliation_strings":["School of Electrical and Computer Engineering, The University of Sydney,Darlington,NSW,2008"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, The University of Sydney,Darlington,NSW,2008","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100784818"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1381171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.85589998960495,"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":0.85589998960495,"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/T10320","display_name":"Neural Networks and Applications","score":0.7494000196456909,"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":0.7351771593093872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6899908185005188},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5525878071784973},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3778287172317505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3483084440231323}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7351771593093872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899908185005188},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5525878071784973},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3778287172317505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3483084440231323},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vtc2024-spring62846.2024.10683517","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vtc2024-spring62846.2024.10683517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 99th Vehicular Technology Conference (VTC2024-Spring)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1641379095","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2530417694","https://openalex.org/W2535838896","https://openalex.org/W2915117209","https://openalex.org/W3088396143","https://openalex.org/W3114142431","https://openalex.org/W3211802628","https://openalex.org/W6639086533","https://openalex.org/W6676769901","https://openalex.org/W6677834374","https://openalex.org/W6683195989","https://openalex.org/W6692846177","https://openalex.org/W6728757088"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"The":[0,28,148],"utility":[1],"of":[2,25,38,56,71,111,124,154,162],"multiple":[3],"reinforcement":[4],"learning":[5,89,95],"(RL)":[6],"agents":[7,49,72,121],"collaboratively":[8],"training":[9,161],"within":[10,22],"a":[11,35,40,92,105,137],"shared":[12],"environment,":[13],"all":[14,120],"working":[15],"towards":[16],"common":[17],"objectives,":[18],"is":[19,34],"increasingly":[20],"evident":[21],"the":[23,69,81,101,109,112,152,160,166,183],"Internet":[24],"Vehicles":[26],"(IoV).":[27],"multi-agent":[29],"Advantage":[30,143],"Actor-Critic":[31],"(MA2C)":[32],"algorithm":[33,141,150],"prominent":[36],"example":[37],"such":[39,53],"Multi-Agent":[41],"Reinforcement":[42],"Learning":[43],"(MARL)":[44],"system.":[45],"However,":[46,115],"MA2C":[47],"requires":[48],"to":[50,67,165],"share":[51],"policies,":[52],"as":[54,91],"pairs":[55],"states":[57],"and":[58,60,84,195],"actions":[59],"even":[61],"trained":[62],"models,":[63],"among":[64],"neighboring":[65],"agents,":[66],"overcome":[68],"challenge":[70],"having":[73],"only":[74],"partial":[75],"observations.":[76],"Unfortunately,":[77],"this":[78,116,133],"requirement":[79],"amplifies":[80],"communication":[82,197],"overhead":[83,198],"raises":[85],"privacy":[86,192],"concerns.":[87],"Federated":[88,145],"(FL),":[90],"privacy-preserving":[93],"machine":[94],"method,":[96],"can":[97],"be":[98,130],"applied":[99],"in":[100,174,186],"MARL":[102],"context":[103],"with":[104],"central":[106],"server":[107],"aggregating":[108],"weights":[110],"agents'":[113,155,168,188,191],"models.":[114],"technique":[117],"assumes":[118],"that":[119],"are":[122],"capable":[123],"executing":[125],"identical":[126],"actions,":[127,189],"which":[128],"may":[129],"impractical.":[131],"In":[132],"paper,":[134],"we":[135],"introduce":[136],"novel":[138],"FL":[139],"A2C":[140],"called":[142],"Actor":[144],"Critic":[146],"(A2FC).":[147],"proposed":[149],"streamlines":[151],"aggregation":[153],"critic":[156],"models":[157,164],"while":[158],"offloading":[159],"actor":[163],"individual":[167],"local":[169],"machines.":[170],"An":[171],"experiment":[172],"conducted":[173],"an":[175],"adaptive":[176],"traffic":[177],"signal":[178],"control":[179],"(ATSC)":[180],"system":[181],"demonstrates":[182],"method's":[184],"effectiveness":[185],"personalizing":[187],"preserving":[190],"during":[193],"training,":[194],"mitigating":[196],"issues.":[199]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}