{"id":"https://openalex.org/W7127593127","doi":"https://doi.org/10.1109/ccnc65079.2026.11366321","title":"Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams","display_name":"Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams","publication_year":2026,"publication_date":"2026-01-09","ids":{"openalex":"https://openalex.org/W7127593127","doi":"https://doi.org/10.1109/ccnc65079.2026.11366321"},"language":null,"primary_location":{"id":"doi:10.1109/ccnc65079.2026.11366321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccnc65079.2026.11366321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd Consumer Communications & Networking Conference (CCNC)","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/A5048022541","display_name":"Hung Du","orcid":"https://orcid.org/0000-0003-1415-5786"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hung Du","raw_affiliation_strings":["Deakin University,Applied Artificial Intelligence Initiative (A2I2),Geelong,VIC,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deakin University,Applied Artificial Intelligence Initiative (A2I2),Geelong,VIC,Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036572807","display_name":"Hy Nguyen","orcid":"https://orcid.org/0009-0008-7092-3106"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hy Nguyen","raw_affiliation_strings":["Deakin University,Applied Artificial Intelligence Initiative (A2I2),Geelong,VIC,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deakin University,Applied Artificial Intelligence Initiative (A2I2),Geelong,VIC,Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070118830","display_name":"Srikanth Thudumu","orcid":"https://orcid.org/0000-0002-7848-9008"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Srikanth Thudumu","raw_affiliation_strings":["Institute of Applied Artificial Intelligence and Robotics (IAAIR),Germantown,TN,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Applied Artificial Intelligence and Robotics (IAAIR),Germantown,TN,USA","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030486012","display_name":"Rajesh Vasa","orcid":"https://orcid.org/0000-0003-4805-1467"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rajesh Vasa","raw_affiliation_strings":["Deakin University,Applied Artificial Intelligence Initiative (A2I2),Geelong,VIC,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deakin University,Applied Artificial Intelligence Initiative (A2I2),Geelong,VIC,Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044290815","display_name":"Kon Mouzakis","orcid":"https://orcid.org/0000-0003-4447-5166"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kon Mouzakis","raw_affiliation_strings":["Deakin University,Applied Artificial Intelligence Initiative (A2I2),Geelong,VIC,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deakin University,Applied Artificial Intelligence Initiative (A2I2),Geelong,VIC,Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15206191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.43779999017715454,"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":0.43779999017715454,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.15719999372959137,"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"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.08630000054836273,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8082000017166138},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7143999934196472},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.5821999907493591},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4253999888896942},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.39149999618530273},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.37610000371932983},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3662000000476837},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.35510000586509705}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8082000017166138},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7143999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6402000188827515},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.37610000371932983},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3662000000476837},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35260000824928284},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.3212999999523163},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C9628104","wikidata":"https://www.wikidata.org/wiki/Q788009","display_name":"Autonomous system (mathematics)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2831999957561493},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27079999446868896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccnc65079.2026.11366321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccnc65079.2026.11366321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd Consumer Communications & Networking Conference (CCNC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4283789768","https://openalex.org/W4393160217"],"related_works":[],"abstract_inverted_index":{"Connected":[0],"and":[1,7,22,64,94,108],"autonomous":[2],"vehicles":[3,35],"across":[4,146],"land,":[5],"water,":[6],"air":[8],"must":[9],"often":[10],"operate":[11],"in":[12,87,141],"dynamic,":[13],"unpredictable":[14],"environments":[15],"with":[16],"limited":[17],"communication,":[18],"no":[19],"centralized":[20],"control,":[21],"partial":[23],"observability.":[24],"These":[25,128],"real-world":[26],"constraints":[27],"pose":[28],"significant":[29],"challenges":[30],"for":[31],"coordination,":[32],"particularly":[33],"when":[34],"pursue":[36],"individual":[37],"objectives.":[38],"To":[39],"address":[40],"this,":[41],"we":[42],"propose":[43],"a":[44],"decentralized":[45],"Multi-Agent":[46],"Reinforcement":[47],"Learning":[48],"(MARL)":[49],"framework":[50],"that":[51,100],"enables":[52],"vehicles,":[53],"acting":[54],"as":[55,120],"agents,":[56],"to":[57,72,112,137],"communicate":[58],"selectively":[59],"based":[60],"on":[61],"local":[62],"goals":[63],"observations.":[65],"This":[66],"goal-aware":[67],"communication":[68],"strategy":[69],"allows":[70],"agents":[71,124],"share":[73],"only":[74],"relevant":[75],"information,":[76],"enhancing":[77],"collaboration":[78],"while":[79],"respecting":[80],"visibility":[81],"limitations.":[82],"We":[83],"validate":[84],"our":[85,101],"approach":[86],"complex":[88],"multi-agent":[89],"navigation":[90],"tasks":[91],"featuring":[92],"obstacles":[93],"dynamic":[95],"agent":[96],"populations.":[97],"Results":[98],"show":[99],"method":[102],"significantly":[103],"improves":[104],"task":[105,116],"success":[106],"rates":[107],"reduces":[109],"time-to-goal":[110],"compared":[111],"non-cooperative":[113],"baselines.":[114],"Moreover,":[115],"performance":[117],"remains":[118],"stable":[119],"the":[121,131],"number":[122],"of":[123,133],"increases,":[125],"demonstrating":[126],"scalability.":[127],"findings":[129],"highlight":[130],"potential":[132],"decentralized,":[134],"goal-driven":[135],"MARL":[136],"support":[138],"effective":[139],"coordination":[140],"realistic":[142],"multi-vehicle":[143],"systems":[144],"operating":[145],"diverse":[147],"domains.":[148]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-06T00:00:00"}