{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T04:06:04Z","timestamp":1751515564849,"version":"3.41.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"20","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-19951-w","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T06:02:37Z","timestamp":1722492157000},"page":"21945-21963","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DHAA: Distributed heuristic action aware multi-agent path finding in high density scene"],"prefix":"10.1007","volume":"84","author":[{"given":"Dongming","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengbin","family":"Pang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"issue":"2","key":"19951_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3533818","volume":"32","author":"C Birchler","year":"2023","unstructured":"Birchler C, Khatiri S, Derakhshanfar P, Panichella S, Panichella A (2023) Single and multi-objective test cases prioritization for self-driving cars in virtual environments. ACM Trans Software Engr Methodology. 32(2):1\u201330","journal-title":"ACM Trans Software Engr Methodology."},{"doi-asserted-by":"crossref","unstructured":"Bukhamseen A, Alabdullah M, Gaufan KB, Mysorewala M (2023) A warehouse storage and retrieval system using iot and autonomous vehicle. In: 2023 9th International Conference on Automation, Robotics and Applications (ICARA), pp 346\u2013350 . IEEE","key":"19951_CR2","DOI":"10.1109\/ICARA56516.2023.10125658"},{"doi-asserted-by":"crossref","unstructured":"Beke L, Uribe L, Lara A, Coello CAC, Weiszer M, Burke EK, Chen J (2023) Routing and scheduling in multigraphs with time constraints-a memetic approach for airport ground movement. IEEE Trans Evolution Compu","key":"19951_CR3","DOI":"10.1109\/TEVC.2023.3262743"},{"issue":"11","key":"19951_CR4","doi-asserted-by":"publisher","first-page":"13677","DOI":"10.1007\/s10489-022-04105-y","volume":"53","author":"A Oroojlooy","year":"2023","unstructured":"Oroojlooy A, Hajinezhad D (2023) A review of cooperative multi-agent deep reinforcement learning. Appl Intell 53(11):13677\u201313722","journal-title":"Appl Intell"},{"doi-asserted-by":"crossref","unstructured":"Yun WJ, Park J, Kim J (2023) Quantum multi-agent meta reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 37, pp 11087\u201311095","key":"19951_CR5","DOI":"10.1609\/aaai.v37i9.26313"},{"issue":"7","key":"19951_CR6","doi-asserted-by":"publisher","first-page":"7033","DOI":"10.1109\/TVT.2022.3169907","volume":"71","author":"G-P Antonio","year":"2022","unstructured":"Antonio G-P, Maria-Dolores C (2022) Multi-agent deep reinforcement learning to manage connected autonomous vehicles at tomorrow\u2019s intersections. IEEE Trans Veh Technol 71(7):7033\u20137043","journal-title":"IEEE Trans Veh Technol"},{"doi-asserted-by":"crossref","unstructured":"Okumura K (2023) Lacam: Search-based algorithm for quick multi-agent pathfinding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 37, pp 11655\u201311662","key":"19951_CR7","DOI":"10.1609\/aaai.v37i10.26377"},{"doi-asserted-by":"crossref","unstructured":"Huang T, Li J, Koenig S, Dilkina B (2022) Anytime multi-agent path finding via machine learning-guided large neighborhood search. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 36, pp 9368\u20139376","key":"19951_CR8","DOI":"10.1609\/aaai.v36i9.21168"},{"doi-asserted-by":"crossref","unstructured":"Leet C, Li J, Koenig S (2022) Shard systems: Scalable, robust and persistent multi-agent path finding with performance guarantees. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 36, pp 9386\u20139395","key":"19951_CR9","DOI":"10.1609\/aaai.v36i9.21170"},{"key":"19951_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2022.03.003","volume":"85","author":"P Ladosz","year":"2022","unstructured":"Ladosz P, Weng L, Kim M, Oh H (2022) Exploration in deep reinforcement learning: A survey. Information Fusion. 85:1\u201322","journal-title":"Information Fusion."},{"key":"19951_CR11","first-page":"21314","volume":"35","author":"H Le","year":"2022","unstructured":"Le H, Wang Y, Gotmare AD, Savarese S, Hoi SCH (2022) Coderl: Mastering code generation through pretrained models and deep reinforcement learning. Adv Neural Inf Process Syst 35:21314\u201321328","journal-title":"Adv Neural Inf Process Syst"},{"doi-asserted-by":"crossref","unstructured":"Hao J, Yang T, Tang H, Bai C, Liu J, Meng Z, Liu P, Wang Z (2023) Exploration in deep reinforcement learning: From single-agent to multiagent domain. IEEE Trans Neural Netw Learn Syst","key":"19951_CR12","DOI":"10.1109\/TNNLS.2023.3236361"},{"doi-asserted-by":"crossref","unstructured":"Cui W, Yu W (2023) Reinforcement learning with non-cumulative objective. IEEE Trans Machine Learn Commu Netw","key":"19951_CR13","DOI":"10.1109\/TMLCN.2023.3285543"},{"key":"19951_CR14","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/j.neunet.2022.12.022","volume":"161","author":"Z Feng","year":"2023","unstructured":"Feng Z, Huang M, Wu Y, Wu D, Cao J, Korovin I, Gorbachev S, Gorbacheva N (2023) Approximating nash equilibrium for anti-uav jamming markov game using a novel event-triggered multi-agent reinforcement learning. Neural Netw 161:330\u2013342","journal-title":"Neural Netw"},{"doi-asserted-by":"crossref","unstructured":"Kumari, Aparna, Kakkar, Riya, Tanwar, Sudeep, Garg, Deepak, Polkowski, Zdzislaw, Alqahtani, Fayez, Tolba (2024) Amr: Multi-agent-based decentralized residential energy management using Deep Reinforcement Learning. J Build Engr 87:109031","key":"19951_CR15","DOI":"10.1016\/j.jobe.2024.109031"},{"doi-asserted-by":"crossref","unstructured":"Kumari, Aparna, Trivedi, Mihir, Tanwar, Sudeep, Sharma, Gulshan, Sharma, Ravi (2022) others: Sv2g-et: A secure vehicle-to-grid energy trading scheme using deep reinforcement learning. Int Trans Elect Energy Syst 2022","key":"19951_CR16","DOI":"10.1155\/2022\/9761157"},{"key":"19951_CR17","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neunet.2023.04.043","volume":"164","author":"W Qi","year":"2023","unstructured":"Qi W, Fan H, Karimi HR, Su H (2023) An adaptive reinforcement learning-based multimodal data fusion framework for human-robot confrontation gaming. Neural Netw 164:489\u2013496","journal-title":"Neural Netw"},{"doi-asserted-by":"crossref","unstructured":"Barer M, Sharon G, Stern R, Felner A (2014) Suboptimal variants of the conflict-based search algorithm for the multi-agent pathfinding problem. In: Proceedings of the International Symposium on Combinatorial Search, vol 5, pp 19\u201327","key":"19951_CR18","DOI":"10.1609\/socs.v5i1.18315"},{"doi-asserted-by":"crossref","unstructured":"Stern R, Sturtevant N, Felner A, Koenig S, Ma H, Walker T, Li J, Atzmon D, Cohen L, Kumar T, et al (2019) Multi-agent pathfinding: Definitions, variants, and benchmarks. In: Proceedings of the International Symposium on Combinatorial Search, vol 10, pp 151\u2013158","key":"19951_CR19","DOI":"10.1609\/socs.v10i1.18510"},{"doi-asserted-by":"crossref","unstructured":"Li J, Felner A, Boyarski E, Ma H, Koenig S (2019) Improved heuristics for multi-agent path finding with conflict-based search. In: IJCAI, vol 2019, pp 442\u2013449","key":"19951_CR20","DOI":"10.24963\/ijcai.2019\/63"},{"doi-asserted-by":"crossref","unstructured":"Li J, Ruml W, Koenig S (2021) Eecbs: A bounded-suboptimal search for multi-agent path finding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 35, pp 12353\u201312362","key":"19951_CR21","DOI":"10.1609\/aaai.v35i14.17466"},{"doi-asserted-by":"crossref","unstructured":"Han D, Pan X, Han Y, Song S, Huang G (2023) Flatten transformer: Vision transformer using focused linear attention. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 5961\u20135971","key":"19951_CR22","DOI":"10.1109\/ICCV51070.2023.00548"},{"doi-asserted-by":"crossref","unstructured":"Hassani A, Walton S, Li J, Li S, Shi H (2023) Neighborhood attention transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6185\u20136194","key":"19951_CR23","DOI":"10.1109\/CVPR52729.2023.00599"},{"doi-asserted-by":"crossref","unstructured":"Kumari, Apama, Tanwar, Sudeep (2021) Al-based peak load reduction approach for residential buildings using reinforcement learning. In: 2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), pp 972\u2013977 . IEEE","key":"19951_CR24","DOI":"10.1109\/ICCCIS51004.2021.9397241"},{"doi-asserted-by":"crossref","unstructured":"Kumari, Aparna, Tanwar, Sudeep (2021) Reinforcement learning for multiagent-based residential energy management system. In: 2021 IEEE Globecom Workshops (GC Wkshps), pp 1\u20136 . IEEE","key":"19951_CR25","DOI":"10.1109\/GCWkshps52748.2021.9682182"},{"unstructured":"Witt CS, Gupta T, Makoviichuk D, Makoviychuk V, Torr PH, Sun M, Whiteson S (2020) Is independent learning all you need in the starcraft multi-agent challenge? arXiv:2011.09533","key":"19951_CR26"},{"key":"19951_CR27","first-page":"24611","volume":"35","author":"C Yu","year":"2022","unstructured":"Yu C, Velu A, Vinitsky E, Gao J, Wang Y, Bayen A, Wu Y (2022) The surprising effectiveness of ppo in cooperative multi-agent games. Adv Neural Inf Process Syst 35:24611\u201324624","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"19951_CR28","first-page":"71","volume":"14","author":"BH Abed-Alguni","year":"2016","unstructured":"Abed-Alguni BH, Paul DJ, Chalup SK, Henskens FA (2016) A comparison study of cooperative q-learning algorithms for independent learners. Int J Artif Intell 14(1):71\u201393","journal-title":"Int J Artif Intell"},{"unstructured":"Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ, Tuyls K, et al (2017) Value-decomposition networks for cooperative multi-agent learning. arXiv:1706.05296","key":"19951_CR29"},{"unstructured":"Wang T, Wang J, Zheng C, Zhang C (2019) Learning nearly decomposable value functions via communication minimization. arXiv:1910.05366.","key":"19951_CR30"},{"doi-asserted-by":"crossref","unstructured":"Wu Y, Hong ZH, Zhang L, Li W, Park S-I, Ahn S, Hur N, Iradier, E, Montalban J, Angueira P (2023) Inter-tower communications network signal structure, and interference analysis for terrestrial broadcasting and datacasting. IEEE Trans Broadcast","key":"19951_CR31","DOI":"10.1109\/TBC.2023.3243406"},{"doi-asserted-by":"crossref","unstructured":"Li W, Chen H, Jin B, Tan W, Zha H, Wang X (2022) Multi-agent path finding with prioritized communication learning. In: 2022 International Conference on Robotics and Automation (ICRA), pp 10695\u201310701 . IEEE","key":"19951_CR32","DOI":"10.1109\/ICRA46639.2022.9811643"},{"doi-asserted-by":"crossref","unstructured":"Zhang S, Li J, Huang T, Koenig S, Dilkina B (2022) Learning a priority ordering for prioritized planning in multi-agent path finding. In: Proceedings of the International Symposium on Combinatorial Search, vol 15, pp 208\u2013216","key":"19951_CR33","DOI":"10.1609\/socs.v15i1.21769"},{"issue":"42","key":"19951_CR34","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.21105\/joss.01315","volume":"4","author":"HJ Van Veen","year":"2019","unstructured":"Van Veen HJ, Saul N, Eargle D, Mangham SW (2019) Kepler mapper: A flexible python implementation of the mapper algorithm. J Open Source Software. 4(42):1315","journal-title":"J Open Source Software."},{"doi-asserted-by":"crossref","unstructured":"Shen S, Xie L, Zhang Y, Wu G, Zhang H, Yu S (2023) Joint differential game and double deep q\u2013networks for suppressing malware spread in industrial internet of things. IEEE Trans Inf Forensics Secur","key":"19951_CR35","DOI":"10.1109\/TIFS.2023.3307956"},{"doi-asserted-by":"crossref","unstructured":"Yuan L, Wang J, Zhang F, Wang C, Zhang Z, Yu Y, Zhang C (2022) Multi-agent incentive communication via decentralized teammate modeling. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 36, pp 9466\u20139474","key":"19951_CR36","DOI":"10.1609\/aaai.v36i9.21179"},{"issue":"7","key":"19951_CR37","doi-asserted-by":"publisher","first-page":"3797","DOI":"10.1109\/TIT.2014.2320500","volume":"60","author":"T Van Erven","year":"2014","unstructured":"Van Erven T, Harremos P (2014) R\u00e9nyi divergence and kullback-leibler divergence. IEEE Trans Inf Theory 60(7):3797\u20133820","journal-title":"IEEE Trans Inf Theory"},{"doi-asserted-by":"crossref","unstructured":"Tolstaya E, Paulos J, Kumar V, Ribeiro A (2021) Multi-robot coverage and exploration using spatial graph neural networks. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp 8944\u20138950 . IEEE","key":"19951_CR38","DOI":"10.1109\/IROS51168.2021.9636675"},{"issue":"2","key":"19951_CR39","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1109\/LRA.2021.3139145","volume":"7","author":"Z Ma","year":"2021","unstructured":"Ma Z, Luo Y, Pan J (2021) Learning selective communication for multi-agent path finding. IEEE Robotics and Automation Letters. 7(2):1455\u20131462","journal-title":"IEEE Robotics and Automation Letters."},{"key":"19951_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106146","volume":"175","author":"P Shao","year":"2024","unstructured":"Shao P, Wen Y, Tao J (2024) Bayesian hypernetwork collaborates with time-difference evolutional network for temporal knowledge prediction. Neural Netw 175:106146","journal-title":"Neural Netw"},{"unstructured":"Horgan D, Quan J, Budden D, Barth-Maron G, Hessel M, Van\u00a0Hasselt H, Silver D (2018) Distributed prioritized experience replay. arXiv:1803.00933.","key":"19951_CR41"},{"doi-asserted-by":"crossref","unstructured":"Zhong X, Li J, Koenig S, Ma H (2022) Optimal and bounded-suboptimal multi-goal task assignment and path finding. In: 2022 International Conference on Robotics and Automation (ICRA), pp 10731\u201310737 . IEEE","key":"19951_CR42","DOI":"10.1109\/ICRA46639.2022.9812020"},{"doi-asserted-by":"crossref","unstructured":"Sartoretti G, Wu Y, Paivine W, Kumar TS, Koenig S, Choset H (2019) Distributed reinforcement learning for multi-robot decentralized collective construction. In: Distributed Autonomous Robotic Systems: The 14th International Symposium, pp 35\u201349 . Springer","key":"19951_CR43","DOI":"10.1007\/978-3-030-05816-6_3"},{"unstructured":"Zhiyao L, Sartoretti G (2020) Deep reinforcement learning based multiagent pathfinding. Technical Report","key":"19951_CR44"},{"key":"19951_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2014.11.001","volume":"219","author":"G Wagner","year":"2015","unstructured":"Wagner G, Choset H (2015) Subdimensional expansion for multirobot path planning. Artif Intell 219:1\u201324","journal-title":"Artif Intell"},{"issue":"3","key":"19951_CR46","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1109\/LRA.2019.2903261","volume":"4","author":"G Sartoretti","year":"2019","unstructured":"Sartoretti G, Kerr J, Shi Y, Wagner G, Kumar TS, Koenig S, Choset H (2019) Primal: Pathfinding via reinforcement and imitation multi-agent learning. IEEE Robot Automat Lett 4(3):2378\u20132385","journal-title":"IEEE Robot Automat Lett"},{"issue":"4","key":"19951_CR47","doi-asserted-by":"publisher","first-page":"3234","DOI":"10.1109\/TASE.2021.3114327","volume":"19","author":"Z Liu","year":"2021","unstructured":"Liu Z, Liu Q, Tang L, Jin K, Wang H, Liu M, Wang H (2021) Visuomotor reinforcement learning for multirobot cooperative navigation. IEEE Trans Autom Sci Eng 19(4):3234\u20133245","journal-title":"IEEE Trans Autom Sci Eng"},{"doi-asserted-by":"crossref","unstructured":"Ma Z, Luo Y, Ma H (2021) Distributed heuristic multi-agent path finding with communication. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp 8699\u20138705 . IEEE","key":"19951_CR48","DOI":"10.1109\/ICRA48506.2021.9560748"},{"unstructured":"Niu Y, Paleja RR, Gombolay MC (2021) Multi-agent graph-attention communication and teaming. In: AAMAS, vol 21, p 20","key":"19951_CR49"},{"doi-asserted-by":"crossref","unstructured":"Lin Q, Ma H (2023) Sacha: Soft actor-critic with heuristic-based attention for partially observable multi-agent path finding. IEEE Robot Automat Lett","key":"19951_CR50","DOI":"10.1109\/LRA.2023.3292004"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19951-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19951-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19951-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T11:22:12Z","timestamp":1751455332000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19951-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,1]]},"references-count":50,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["19951"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19951-w","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2024,8,1]]},"assertion":[{"value":"26 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No conflict of interest exits in the submission of this manuscript, and manuscriptis approved by all authors for publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"This paper strictly abides by the moral standards of this journal.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"All the authors of this paper have reviewed and agreed to contribute to yourjournal by consensus.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Once this paper is hired, we agree to publish it in your journal.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}