{"id":"https://openalex.org/W4416922942","doi":"https://doi.org/10.1109/iccais67508.2025.11262048","title":"Multi-Agent Planning for Pursuing Multiple Objects via Proximal Policy Optimisation","display_name":"Multi-Agent Planning for Pursuing Multiple Objects via Proximal Policy Optimisation","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4416922942","doi":"https://doi.org/10.1109/iccais67508.2025.11262048"},"language":null,"primary_location":{"id":"doi:10.1109/iccais67508.2025.11262048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais67508.2025.11262048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060770511","display_name":"Hoa Van Nguyen","orcid":"https://orcid.org/0000-0002-6878-5102"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hoa Van Nguyen","raw_affiliation_strings":["School of Electrical Engineering, Curtin University,Australia,WA 6102"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Curtin University,Australia,WA 6102","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044691350","display_name":"Diluka Moratuwage","orcid":"https://orcid.org/0000-0001-6614-6967"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I74899385","display_name":"Central Queensland University","ror":"https://ror.org/023q4bk22","country_code":"AU","type":"education","lineage":["https://openalex.org/I74899385"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Diluka Moratuwage","raw_affiliation_strings":["School of Engineering and Technology, Central Queensland University,Australia,QLD 4701"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Technology, Central Queensland University,Australia,QLD 4701","institution_ids":["https://openalex.org/I160993911","https://openalex.org/I74899385"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069386456","display_name":"Tran Thien Dat Nguyen","orcid":"https://orcid.org/0000-0001-9185-4009"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tran Thien Dat Nguyen","raw_affiliation_strings":["School of Electrical Engineering, Curtin University,Australia,WA 6102"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Curtin University,Australia,WA 6102","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072873685","display_name":"Changbeom Shim","orcid":"https://orcid.org/0000-0003-1735-6655"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Changbeom Shim","raw_affiliation_strings":["School of Electrical Engineering, Curtin University,Australia,WA 6102"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Curtin University,Australia,WA 6102","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072792589","display_name":"Ba\u2010Ngu Vo","orcid":"https://orcid.org/0000-0003-4202-7722"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ba-Ngu Vo","raw_affiliation_strings":["School of Electrical Engineering, Curtin University,Australia,WA 6102"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Curtin University,Australia,WA 6102","institution_ids":["https://openalex.org/I205640436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.35401381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"110","last_page":"115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.835099995136261,"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":0.835099995136261,"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/T12158","display_name":"Guidance and Control Systems","score":0.045499999076128006,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11574","display_name":"Artificial Intelligence in Games","score":0.019600000232458115,"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":0.8549000024795532},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6236000061035156},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5927000045776367},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5738000273704529},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5638999938964844},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.491100013256073},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4887000024318695},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4643000066280365}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8549000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7315999865531921},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6078000068664551},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5927000045776367},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5638999938964844},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccais67508.2025.11262048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais67508.2025.11262048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3978379572","display_name":null,"funder_award_id":"LP200301507","funder_id":"https://openalex.org/F4320320432","funder_display_name":"Department of Foreign Affairs and Trade, Australian Government"}],"funders":[{"id":"https://openalex.org/F4320320432","display_name":"Department of Foreign Affairs and Trade, Australian Government","ror":"https://ror.org/023wsvq95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W40650588","https://openalex.org/W1641379095","https://openalex.org/W1677859417","https://openalex.org/W1993412827","https://openalex.org/W2088956500","https://openalex.org/W2145339207","https://openalex.org/W2161303196","https://openalex.org/W2979653692","https://openalex.org/W3093345403","https://openalex.org/W3119186746","https://openalex.org/W4383108558","https://openalex.org/W4386824832","https://openalex.org/W4388579832","https://openalex.org/W4400352413"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,26,62],"challenge":[4],"of":[5,49],"efficient":[6],"multiagent":[7],"planning":[8],"for":[9,70,132],"capturing":[10],"multiple":[11],"dynamic":[12,40],"objects":[13,103],"using":[14,61],"deep":[15],"reinforcement":[16,111],"learning":[17,112],"(DRL).":[18],"We":[19],"propose":[20],"a":[21,39,46,67,78,123],"scalable":[22],"solution":[23],"based":[24],"on":[25],"multi-agent":[27,110,130],"proximal":[28],"policy":[29],"optimisation":[30],"(MAPPO)":[31],"with":[32,77],"three":[33],"key":[34],"innovations.":[35],"First,":[36],"we":[37,54],"employ":[38],"state":[41],"representation":[42],"that":[43,92],"adapts":[44],"to":[45,65,83,97],"variable":[47],"number":[48],"objects,":[50],"ensuring":[51],"scalability.":[52],"Second,":[53],"introduce":[55],"an":[56],"optimal":[57],"task":[58],"allocation":[59],"mechanism":[60],"Hungarian":[63],"algorithm":[64],"provide":[66],"cooperative":[68],"signal":[69],"agent":[71],"assignments.":[72],"Finally,":[73],"this":[74],"is":[75],"coupled":[76],"multi-component":[79],"reward":[80],"function":[81],"designed":[82],"incentivise":[84],"both":[85,116],"rapid":[86],"and":[87,99,118],"coordinated":[88],"pursuit.":[89],"Experiments":[90],"demonstrate":[91],"our":[93],"method":[94],"enables":[95],"agents":[96],"efficiently":[98],"collaboratively":[100],"pursue":[101],"all":[102],"across":[104],"various":[105],"scenarios,":[106],"significantly":[107],"outperforming":[108],"strong":[109],"(MARL)":[113],"baselines":[114],"in":[115],"coordination":[117],"efficiency.":[119],"The":[120],"results":[121],"highlight":[122],"practical":[124],"pathway":[125],"toward":[126],"developing":[127],"effective,":[128],"adaptive":[129],"systems":[131],"complex,":[133],"real-world":[134],"tasks.":[135]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-02T00:00:00"}