{"id":"https://openalex.org/W4416798154","doi":"https://doi.org/10.1109/jiot.2025.3638954","title":"MAPG <sup>2</sup> : Multiagent Policy Gradient via Potential Game for Multirobot Task Allocation Problems","display_name":"MAPG <sup>2</sup> : Multiagent Policy Gradient via Potential Game for Multirobot Task Allocation Problems","publication_year":2025,"publication_date":"2025-11-28","ids":{"openalex":"https://openalex.org/W4416798154","doi":"https://doi.org/10.1109/jiot.2025.3638954"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2025.3638954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3638954","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-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/A5100764370","display_name":"Shangdong Yang","orcid":"https://orcid.org/0000-0001-5379-9539"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangdong Yang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5379-9539","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103738457","display_name":"Jin Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Ma","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102714720","display_name":"Hongye Cao","orcid":"https://orcid.org/0000-0002-2537-2295"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongye Cao","raw_affiliation_strings":["Department of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2537-2295","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087374601","display_name":"Xingguo Chen","orcid":"https://orcid.org/0000-0002-8757-1767"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingguo Chen","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8757-1767","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040712173","display_name":"Yansheng Wu","orcid":"https://orcid.org/0000-0002-7234-9119"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansheng Wu","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7234-9119","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101155491","display_name":"Gongzhi Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongzhi Luo","raw_affiliation_strings":["School of Management, anjing University of Posts and Telecommunications, Nanjing, China","School of Management, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-3486-2476","affiliations":[{"raw_affiliation_string":"School of Management, anjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Management, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.1762027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"8","first_page":"15171","last_page":"15185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6486999988555908,"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":0.6486999988555908,"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/T11133","display_name":"UAV Applications and Optimization","score":0.11890000104904175,"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/T13553","display_name":"Age of Information Optimization","score":0.03750000149011612,"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/scalability","display_name":"Scalability","score":0.5690000057220459},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5429999828338623},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5424000024795532},{"id":"https://openalex.org/keywords/soundness","display_name":"Soundness","score":0.5403000116348267},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5047000050544739},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4790000021457672},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4368000030517578},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.43309998512268066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403000235557556},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C39920170","wikidata":"https://www.wikidata.org/wiki/Q693083","display_name":"Soundness","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45399999618530273},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C2778079155","wikidata":"https://www.wikidata.org/wiki/Q288500","display_name":"Potential game","level":3,"score":0.41440001130104065},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36500000953674316},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3638954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3638954","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1607628814","display_name":null,"funder_award_id":"72171124","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G228663136","display_name":null,"funder_award_id":"12441103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3740420203","display_name":null,"funder_award_id":"2242025K30024","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3862649344","display_name":null,"funder_award_id":"62372247","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G669068149","display_name":null,"funder_award_id":"62276142","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7334411499","display_name":null,"funder_award_id":"62206133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"task":[1,22,222],"allocation":[2,23,177,200],"among":[3],"multiple":[4,116],"UAVs":[5],"and":[6,95,118,125,188,205,232],"autonomous":[7],"robots":[8],"is":[9,16,68,112],"critical":[10],"in":[11,121,221],"modern":[12],"IoT":[13],"scenarios.":[14],"This":[15,100],"typically":[17],"modeled":[18],"as":[19,45,179],"a":[20,46,73,103,133,180,218],"multi-robot":[21],"(MRTA)":[24],"problem,":[25,52,108],"known":[26],"to":[27,54,166,184,226],"be":[28],"an":[29],"NP-hard":[30],"combinatorial":[31],"optimization":[32,42],"problem.":[33],"Neural":[34],"sequential":[35],"modeling":[36],"combined":[37],"with":[38],"reinforcement":[39],"learning":[40],"(RL)":[41],"has":[43,83],"emerged":[44],"promising":[47],"paradigm":[48],"for":[49],"solving":[50],"this":[51,129],"owing":[53],"its":[55,230],"high":[56],"efficiency":[57],"during":[58],"inference.":[59],"However,":[60],"most":[61],"existing":[62],"methods":[63],"assume":[64],"that":[65,213],"each":[66,110],"robot":[67,111],"capable":[69,113],"of":[70,76,80,89,97,105,114,152,156,190],"performing":[71],"only":[72],"single":[74],"type":[75],"task.":[77],"The":[78,149],"development":[79],"sensing":[81],"technologies":[82],"significantly":[84],"enhanced":[85],"the":[86,93,106,168,175,186,191],"functional":[87],"diversity":[88],"robots,":[90],"thereby":[91],"challenging":[92],"effectiveness":[94,231],"scalability":[96],"traditional":[98],"methods.":[99],"paper":[101],"considers":[102],"variant":[104],"MRTA":[107],"where":[109],"handling":[115],"tasks,":[117],"tasks":[119],"vary":[120],"both":[122],"their":[123],"types":[124],"required":[126],"resources.":[127],"To":[128],"end,":[130],"we":[131,160,173],"present":[132],"novel":[134],"game-theoretic":[135],"multi-agent":[136,140],"RL":[137],"algorithm":[138],"called":[139],"policy":[141],"gradient":[142],"via":[143],"potential":[144,181],"game":[145,182],"(MAPG<sup":[146],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[147,215],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>).":[148],"key":[150],"components":[151],"proposed":[153],"method":[154],"consist":[155],"three":[157],"parts.":[158],"Firstly,":[159],"utilize":[161],"graph-based":[162],"attention":[163],"model":[164],"(GAM)":[165],"characterize":[167],"representations":[169],"between":[170],"tasks.":[171],"Secondly,":[172],"formulate":[174],"single-step":[176],"process":[178],"(PG)":[183],"guarantee":[185],"consistency":[187],"soundness":[189],"reward":[192],"function":[193],"design.":[194],"Lastly,":[195],"our":[196],"approach":[197],"sequentially":[198],"generates":[199],"strategies":[201],"through":[202],"centralized":[203],"training":[204],"decentralized":[206],"execution":[207],"(CTDE)":[208],"framework.":[209],"Extensive":[210],"experiments":[211],"demonstrate":[212],"MAPG<sup":[214],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[216],"achieves":[217],"10%":[219],"improvement":[220],"completion":[223],"rate":[224],"compared":[225],"state-of-the-art":[227],"baselines,":[228],"validating":[229],"robustness.":[233]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}