{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T14:46:22Z","timestamp":1772635582690,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"28","license":[{"start":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T00:00:00Z","timestamp":1690675200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T00:00:00Z","timestamp":1690675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of China","award":["No.2021YFE014400"],"award-info":[{"award-number":["No.2021YFE014400"]}]},{"DOI":"10.13039\/501100011665","name":"Deanship of Scientific Research, King Saud University","doi-asserted-by":"publisher","award":["RGP-1441-33"],"award-info":[{"award-number":["RGP-1441-33"]}],"id":[{"id":"10.13039\/501100011665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s00521-023-08875-5","type":"journal-article","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T10:01:24Z","timestamp":1690711284000},"page":"21007-21022","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["AGRCNet: communicate by attentional graph relations in multi-agent reinforcement learning for traffic signal control"],"prefix":"10.1007","volume":"35","author":[{"given":"Tinghuai","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2712-9088","authenticated-orcid":false,"given":"Kexing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Rong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yurong","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,30]]},"reference":[{"key":"8875_CR1","doi-asserted-by":"crossref","unstructured":"Fan Z, Huang D, Xu K et\u00a0al (2022) Comparative analysis of rail transit braking digital command control strategies based on neural network. Neural Comput Appl 1\u201313","DOI":"10.1007\/s00521-022-07552-3"},{"issue":"24","key":"8875_CR2","doi-asserted-by":"publisher","first-page":"17,535","DOI":"10.1007\/s00521-021-06341-8","volume":"33","author":"CW Tsai","year":"2021","unstructured":"Tsai CW, Teng TC, Liao JT et al (2021) An effective hybrid-heuristic algorithm for urban traffic light scheduling. Neural Comput Appl 33(24):17,535-17,549","journal-title":"Neural Comput Appl"},{"key":"8875_CR3","doi-asserted-by":"crossref","unstructured":"Suau M, He J, Congeduti E et\u00a0al (2022) Influence-aware memory architectures for deep reinforcement learning in pomdps. Neural Comput Appl 1\u201317","DOI":"10.1007\/s00521-022-07691-7"},{"key":"8875_CR4","doi-asserted-by":"crossref","unstructured":"Li M, Cai Z, Zhao J et\u00a0al (2022) Disturbance rejection and high dynamic quadrotor control based on reinforcement learning and supervised learning. Neural Comput Appl 1\u201321","DOI":"10.1007\/s00521-022-07033-7"},{"issue":"9","key":"8875_CR5","doi-asserted-by":"publisher","first-page":"7227","DOI":"10.1007\/s00521-021-06855-1","volume":"34","author":"J Jia","year":"2022","unstructured":"Jia J, Yu R, Du Z et al (2022) Distributed localization for iot with multi-agent reinforcement learning. Neural Comput Appl 34(9):7227\u20137240","journal-title":"Neural Comput Appl"},{"issue":"8","key":"8875_CR6","doi-asserted-by":"publisher","first-page":"6215","DOI":"10.1007\/s00521-021-06801-1","volume":"34","author":"Y Cui","year":"2022","unstructured":"Cui Y, Liu X (2022) Adaptive consensus tracking control of strict-feedback nonlinear multi-agent systems with unknown dynamic leader. Neural Comput Appl 34(8):6215\u20136226","journal-title":"Neural Comput Appl"},{"key":"8875_CR7","doi-asserted-by":"crossref","unstructured":"Fang Y, Chen P et\u00a0al (2022) Hint: harnessing the wisdom of crowds for handling multi-phase tasks. Neural Comput Appl 1\u201323","DOI":"10.1007\/s00521-021-06825-7"},{"key":"8875_CR8","doi-asserted-by":"crossref","unstructured":"Gronauer S, Diepold K (2022) Multi-agent deep reinforcement learning: a survey. Artif Intell Rev 1\u201349","DOI":"10.1007\/s10462-021-09996-w"},{"key":"8875_CR9","doi-asserted-by":"crossref","unstructured":"Mishra S, Arora A (2022) A huber reward function-driven deep reinforcement learning solution for cart-pole balancing problem. Neural Comput Appl 1\u201318","DOI":"10.1007\/s00521-022-07606-6"},{"key":"8875_CR10","doi-asserted-by":"crossref","unstructured":"Liu W, Liu S, Cao J et\u00a0al (2021) Learning communication for cooperation in dynamic agent-number environment. IEEE\/ASME Trans Mechatron","DOI":"10.1109\/TMECH.2021.3076080"},{"key":"8875_CR11","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neucom.2020.08.054","volume":"420","author":"R Ceren","year":"2021","unstructured":"Ceren R, He K, Doshi P et al (2021) Palo bounds for reinforcement learning in partially observable stochastic games. Neurocomputing 420:36\u201356","journal-title":"Neurocomputing"},{"issue":"2","key":"8875_CR12","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/JSAIT.2021.3078754","volume":"2","author":"S Qiu","year":"2021","unstructured":"Qiu S, Yang Z, Ye J et al (2021) On finite-time convergence of actor-critic algorithm. IEEE J Sel Areas Inf Theory 2(2):652\u2013664","journal-title":"IEEE J Sel Areas Inf Theory"},{"key":"8875_CR13","doi-asserted-by":"crossref","unstructured":"Ye Y, Ji S (2021) Sparse graph attention networks. IEEE Trans Knowl Data Eng","DOI":"10.1109\/TKDE.2021.3072345"},{"key":"8875_CR14","doi-asserted-by":"crossref","unstructured":"Chen Z, Xu J, Peng T, et\u00a0al (2021) Graph convolutional network-based method for fault diagnosis using a hybrid of measurement and prior knowledge. IEEE Trans Cybern","DOI":"10.1109\/TCYB.2021.3059002"},{"key":"8875_CR15","doi-asserted-by":"crossref","unstructured":"Jiang S, Huang Y, Jafari M, et\u00a0al (2021) A distributed multi-agent reinforcement learning with graph decomposition approach for large-scale adaptive traffic signal control. IEEE Trans Intell Transp Syst","DOI":"10.1109\/TITS.2021.3131596"},{"key":"8875_CR16","doi-asserted-by":"crossref","unstructured":"Li J, Ma H, Zhang Z et\u00a0al (2021) Spatio-temporal graph dual-attention network for multi-agent prediction and tracking. IEEE Trans Intell Transp Syst","DOI":"10.1109\/TITS.2021.3094821"},{"key":"8875_CR17","doi-asserted-by":"crossref","unstructured":"Lopez PA, Behrisch M, Bieker-Walz L et\u00a0al (2018) Microscopic traffic simulation using sumo. In: 2018 21st International conference on intelligent transportation systems (ITSC). IEEE, pp 2575\u20132582","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"8875_CR18","first-page":"6379","volume":"30","author":"R Lowe","year":"2017","unstructured":"Lowe R, Wu Y, Tamar A et al (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. Adv Neural Inf Process Syst 30:6379\u20136390","journal-title":"Adv Neural Inf Process Syst"},{"key":"8875_CR19","doi-asserted-by":"crossref","unstructured":"Oroojlooy A, Hajinezhad D (2022) A review of cooperative multi-agent deep reinforcement learning. Appl Intell pp 1\u201346","DOI":"10.1007\/s10489-022-04105-y"},{"key":"8875_CR20","first-page":"2244","volume":"29","author":"S Sukhbaatar","year":"2016","unstructured":"Sukhbaatar S, Fergus R et al (2016) Learning multiagent communication with backpropagation. Adv Neural Inf Process Syst 29:2244\u20132252","journal-title":"Adv Neural Inf Process Syst"},{"key":"8875_CR21","unstructured":"Peng P, Wen Y, Yang Y et\u00a0al (2017) Multiagent bidirectionally-coordinated nets: emergence of human-level coordination in learning to play starcraft combat games. arXiv preprint arXiv:1703.10069"},{"key":"8875_CR22","doi-asserted-by":"crossref","unstructured":"Yu Z, Tan P, Sun Q et\u00a0al (2021) Longitudinal wind field prediction based on ddpg. Neural Comput Appl 1\u201313","DOI":"10.1007\/s00521-021-06356-1"},{"issue":"5","key":"8875_CR23","doi-asserted-by":"publisher","first-page":"4839","DOI":"10.1109\/TVT.2021.3055895","volume":"70","author":"MA Khan","year":"2021","unstructured":"Khan MA, Ullah I, Kumar N et al (2021) An efficient and secure certificate-based access control and key agreement scheme for flying ad-hoc networks. IEEE Trans Veh Technol 70(5):4839\u20134851","journal-title":"IEEE Trans Veh Technol"},{"key":"8875_CR24","unstructured":"Kim D, Moon S, Hostallero D et\u00a0al (2019) Learning to schedule communication in multi-agent reinforcement learning. arXiv preprint arXiv:1902.01554"},{"key":"8875_CR25","unstructured":"Iqbal S, Sha F (2019) Actor-attention-critic for multi-agent reinforcement learning. In: International conference on machine learning. PMLR, pp 2961\u20132970"},{"key":"8875_CR26","unstructured":"Singh A, Jain T, Sukhbaatar S (2018) Learning when to communicate at scale in multiagent cooperative and competitive tasks. In: International conference on learning representations"},{"key":"8875_CR27","unstructured":"Kim D, Moon S, Hostallero D et\u00a0al (2018) Learning to schedule communication in multi-agent reinforcement learning. In: International conference on learning representations"},{"key":"8875_CR28","doi-asserted-by":"crossref","unstructured":"Pesce E, Montana G (2020) Improving coordination in small-scale multi-agent deep reinforcement learning through memory-driven communication. Mach Learn 1\u201321","DOI":"10.1007\/s10994-019-05864-5"},{"key":"8875_CR29","unstructured":"Das A, Gervet T, Romoff J et\u00a0al (2019) Tarmac: targeted multi-agent communication. In: International conference on machine learning. PMLR, pp 1538\u20131546"},{"key":"8875_CR30","unstructured":"Jiang J, Lu Z (2018) Learning attentional communication for multi-agent cooperation. arXiv preprint arXiv:1805.07733"},{"key":"8875_CR31","doi-asserted-by":"crossref","unstructured":"Zhang C, Jin S, Xue W et\u00a0al (2021) Independent reinforcement learning for weakly cooperative multiagent traffic control problem. IEEE Trans Veh Technol","DOI":"10.1109\/TVT.2021.3090796"},{"key":"8875_CR32","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1016\/j.neucom.2021.11.106","volume":"490","author":"B Liu","year":"2022","unstructured":"Liu B, Ding Z (2022) A distributed deep reinforcement learning method for traffic light control. Neurocomputing 490:390\u2013399","journal-title":"Neurocomputing"},{"issue":"113","key":"8875_CR33","first-page":"820","volume":"164","author":"S Carta","year":"2021","unstructured":"Carta S, Ferreira A, Podda AS et al (2021) Multi-dqn: an ensemble of deep q-learning agents for stock market forecasting. Expert Syst Appl 164(113):820","journal-title":"Expert Syst Appl"},{"key":"8875_CR34","doi-asserted-by":"crossref","unstructured":"Ge H, Gao D, Sun L et\u00a0al (2021) Multi-agent transfer reinforcement learning with multi-view encoder for adaptive traffic signal control. IEEE Trans Intell Transp Syst","DOI":"10.1109\/TITS.2021.3115240"},{"key":"8875_CR35","doi-asserted-by":"crossref","unstructured":"Chen YH, Huang L, Wang CD et\u00a0al (2021) Hybrid-order gated graph neural network for session-based recommendation. IEEE Trans Ind Inform","DOI":"10.1109\/TII.2021.3091435"},{"key":"8875_CR36","unstructured":"Wang T, Liao R, Ba J et\u00a0al (2018) Nervenet: learning structured policy with graph neural networks. In: International conference on learning representations"},{"key":"8875_CR37","unstructured":"You J, Liu B, Ying R et\u00a0al (2018) Graph convolutional policy network for goal-directed molecular graph generation. In: Proceedings of the 32nd international conference on neural information processing systems, pp 6412\u20136422"},{"issue":"6","key":"8875_CR38","doi-asserted-by":"publisher","first-page":"2198","DOI":"10.1039\/D0SC04823B","volume":"12","author":"Y Guan","year":"2021","unstructured":"Guan Y, Coley CW, Wu H et al (2021) Regio-selectivity prediction with a machine-learned reaction representation and on-the-fly quantum mechanical descriptors. Chem Sci 12(6):2198\u20132208","journal-title":"Chem Sci"},{"key":"8875_CR39","doi-asserted-by":"crossref","unstructured":"Liu Y, Wang W, Hu Y, et\u00a0al (2020) Multi-agent game abstraction via graph attention neural network. In: Proceedings of the AAAI conference on artificial intelligence, pp 7211\u20137218","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"8875_CR40","doi-asserted-by":"crossref","unstructured":"Yin P, Ji D, Yan H et\u00a0al (2022) Multimodal deep collaborative filtering recommendation based on dual attention. Neural Comput Appl 1\u201314","DOI":"10.1007\/s00521-022-07756-7"},{"key":"8875_CR41","doi-asserted-by":"crossref","unstructured":"Chandaliya PK, Nain N (2022) Aw-gan: face aging and rejuvenation using attention with wavelet gan. Neural Comput Appl 1\u201315","DOI":"10.1007\/s00521-022-07721-4"},{"key":"8875_CR42","doi-asserted-by":"crossref","unstructured":"Nikolaidis S, Refanidis I (2022) Consolidating incentivization in distributed neural network training via decentralized autonomous organization. Neural Comput Appl 1\u201315","DOI":"10.1007\/s00521-022-07374-3"},{"key":"8875_CR43","doi-asserted-by":"crossref","unstructured":"Girihagama L, Naveed\u00a0Khaliq M, Lamontagne P et\u00a0al (2022) Streamflow modelling and forecasting for canadian watersheds using lstm networks with attention mechanism. Neural Comput Appl 1\u201321","DOI":"10.1007\/s00521-022-07523-8"},{"key":"8875_CR44","unstructured":"Liu Y, Zhang K, Basar T et\u00a0al (2020) An improved analysis of (variance-reduced) policy gradient and natural policy gradient methods. In: NeurIPS"},{"key":"8875_CR45","unstructured":"Li S, Gupta JK, Morales P, et\u00a0al (2021) Deep implicit coordination graphs for multi-agent reinforcement learning. In: Proceedings of the 20th international conference on autonomous agents and multiagent systems, pp 764\u2013772"},{"issue":"104","key":"8875_CR46","first-page":"052","volume":"97","author":"DM Vo","year":"2021","unstructured":"Vo DM, Nguyen DM, Lee SW (2021) Deep softmax collaborative representation for robust degraded face recognition. Eng Appl Artif Intell 97(104):052","journal-title":"Eng Appl Artif Intell"},{"issue":"120","key":"8875_CR47","first-page":"451","volume":"227","author":"J Chen","year":"2021","unstructured":"Chen J, Feng X, Jiang L et al (2021) State of charge estimation of lithium-ion battery using denoising autoencoder and gated recurrent unit recurrent neural network. Energy 227(120):451","journal-title":"Energy"},{"issue":"1","key":"8875_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11704-020-9153-6","volume":"15","author":"HY Huang","year":"2021","unstructured":"Huang HY, Kim KT, Youn HY (2021) Determining node duty cycle using q-learning and linear regression for wsn. Front Comput Sci 15(1):1\u20137","journal-title":"Front Comput Sci"},{"key":"8875_CR49","doi-asserted-by":"crossref","unstructured":"Wang M, Wu L, Li J, et\u00a0al (2021) Traffic signal control with reinforcement learning based on region-aware cooperative strategy. IEEE Trans Intell Transp Syst","DOI":"10.1109\/TITS.2021.3062072"},{"key":"8875_CR50","doi-asserted-by":"crossref","unstructured":"Strypsteen T, Bertrand A (2021) End-to-end learnable eeg channel selection for deep neural networks with gumbel-softmax. J Neural Eng","DOI":"10.1088\/1741-2552\/ac115d"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08875-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08875-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08875-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T00:24:38Z","timestamp":1693355078000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08875-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,30]]},"references-count":50,"journal-issue":{"issue":"28","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["8875"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08875-5","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,30]]},"assertion":[{"value":"19 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors approve that the research presented in this paper is conducted following the principles of ethical and professional conduct.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}