{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:51:49Z","timestamp":1775854309658,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206133"],"award-info":[{"award-number":["62206133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372247"],"award-info":[{"award-number":["62372247"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12441103"],"award-info":[{"award-number":["12441103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276142"],"award-info":[{"award-number":["62276142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72171124"],"award-info":[{"award-number":["72171124"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2242025K30024"],"award-info":[{"award-number":["2242025K30024"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Fund of National Mobile Communications Research Laboratory, Southeast University","award":["2025D01"],"award-info":[{"award-number":["2025D01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,4,15]]},"DOI":"10.1109\/jiot.2025.3638954","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:44:07Z","timestamp":1764355447000},"page":"15171-15185","source":"Crossref","is-referenced-by-count":0,"title":["MAPG\n                    <sup>2<\/sup>\n                    : Multiagent Policy Gradient via Potential Game for Multirobot Task Allocation Problems"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5379-9539","authenticated-orcid":false,"given":"Shangdong","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2537-2295","authenticated-orcid":false,"given":"Hongye","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8757-1767","authenticated-orcid":false,"given":"Xingguo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7234-9119","authenticated-orcid":false,"given":"Yansheng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3486-2476","authenticated-orcid":false,"given":"Gongzhi","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Management, anjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364904045564"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3522901"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3525640"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3397823"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3409169"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01803-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.10.008"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2018-86161"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611973594","volume-title":"Vehicle Routing: Problems, Methods, and Applications","author":"Toth","year":"2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.876939"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2009.03.008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MRS.2019.8901062"},{"key":"ref13","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Vinyals"},{"key":"ref14","article-title":"Neural combinatorial optimization with reinforcement learning","author":"Bello","year":"2016","journal-title":"arXiv:1611.09940"},{"key":"ref15","first-page":"9861","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"31","author":"Nazari"},{"key":"ref16","first-page":"1","article-title":"Attention, learn to solve routing problems!","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kool"},{"key":"ref17","first-page":"21188","article-title":"POMO: Policy optimization with multiple optima for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kwon"},{"key":"ref18","article-title":"Efficient active search for combinatorial optimization problems","author":"Hottung","year":"2021","journal-title":"arXiv:2106.05126"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977661"},{"key":"ref20","first-page":"1936","article-title":"Sym-NCO: Leveraging symmetricity for neural combinatorial optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref21","article-title":"RL4CO: An extensive reinforcement learning for combinatorial optimization benchmark","author":"Berto","year":"2023","journal-title":"arXiv:2306.17100"},{"key":"ref22","first-page":"7947","article-title":"Combinatorial optimization with policy adaptation using latent space search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chalumeau"},{"key":"ref23","article-title":"PolyNet: Learning diverse solution strategies for neural combinatorial optimization","author":"Hottung","year":"2024","journal-title":"arXiv:2402.14048"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3556831"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.2181683"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s22051824"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1006\/game.1996.0044"},{"key":"ref28","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. Adapt. Agents Multi-Agent Syst.","author":"Sunehag"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CSCE60160.2023.00053"},{"key":"ref30","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2018.8812329"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3308593"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CyberC55534.2022.00054"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIA59741.2023.00020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2959327"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2438032"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3321605"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICoIAS53694.2021.00082"},{"key":"ref39","article-title":"Extnco: A fine-grained divide-and-conquer approach for extending nco to solve large-scale traveling salesman problem","author":"Chen","year":"2023","journal-title":"Available SSRN"},{"key":"ref40","first-page":"48485","article-title":"Winner takes it all: Training performant RL populations for combinatorial optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Grinsztajn"},{"key":"ref41","first-page":"43706","article-title":"DeepACO: Neural-enhanced ant systems for combinatorial optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ye"},{"key":"ref42","first-page":"11096","article-title":"Learning to iteratively solve routing problems with dual-aspect collaborative transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2157"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2006.345353"},{"issue":"1","key":"ref46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0269888912000057","article-title":"Independent reinforcement learners in cooperative Markov games: A survey regarding coordination problems","volume":"27","author":"Matignon","year":"2012","journal-title":"Knowl. Eng. Rev."},{"key":"ref47","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref49","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/YAC57282.2022.10023568"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IMCEC51613.2021.9482235"},{"key":"ref52","volume-title":"Game Theory","author":"Owen","year":"2013"},{"issue":"7","key":"ref53","doi-asserted-by":"crossref","first-page":"1793","DOI":"10.1016\/j.automatica.2014.05.005","article-title":"On finite potential games","volume":"50","author":"Cheng","year":"2014","journal-title":"Automatica"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.36.1.48"},{"key":"ref55","volume":"13","author":"Pareto","year":"1919","journal-title":"Manuale Di Economia Politica Con Una Introduzione Alla Scienza Sociale"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3516583"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3006620"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2023.10.003"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3093874"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104492"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2023.102620"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2445780"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref64","first-page":"15650","article-title":"Reinforcement learning with state observation costs in action-contingent noiselessly observable Markov decision processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Nam"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812370"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC64304.2024.10987816"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11477814\/11271511.pdf?arnumber=11271511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:00:15Z","timestamp":1775851215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,15]]},"references-count":66,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3638954","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,15]]}}}