{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T05:20:41Z","timestamp":1764134441801,"version":"3.46.0"},"reference-count":42,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42471506"],"award-info":[{"award-number":["42471506"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004761","name":"Provincial Natural Science Foundation of Hunan","doi-asserted-by":"crossref","award":["2025JJ40034"],"award-info":[{"award-number":["2025JJ40034"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Changsha Distinguished Young Science and Technology Talent Program","award":["kq2506011"],"award-info":[{"award-number":["kq2506011"]}]},{"name":"Funds of Open Projects of Hunan Geospatial Information Engineering and Technology Research Center","award":["HNGIET2024004"],"award-info":[{"award-number":["HNGIET2024004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Rational location planning of express delivery stations (EDS) is crucial for enhancing the quality and efficiency of urban logistics. The spatial heterogeneity of logistics demand across urban areas highlights the importance of adopting a scientific approach to EDS location planning. To tackle the issue of strategy misalignment caused by heterogeneous demand scenarios, this study proposes a continuous location method for EDS based on multi-agent deep reinforcement learning. The method formulates the location problem as a continuous maximum coverage model and trains multiple agents with diverse policies to enable adaptive decision-making in complex urban environments. A direction-controlled continuous movement mechanism is introduced to facilitate an efficient search and high-precision location planning. Additionally, a perception system based on local observation is designed to rapidly capture heterogeneous environmental features, while a local\u2013global reward feedback mechanism is established to balance localized optimization with overall system benefits. Case studies conducted in Fuzhou, Fujian Province and Shenzhen, Guangdong Province, China, demonstrate that the proposed method significantly outperforms traditional heuristic methods and the single-agent deep reinforcement learning method in terms of both coverage rate and computational efficiency, achieving an increase in population coverage of 9.63 and 15.99 percentage points, respectively. Furthermore, by analyzing the relationship between the number of stations and coverage effectiveness, this study identifies optimal station configuration thresholds for different urban areas. The findings provide a scientific basis for investment decision-making and location planning in EDS construction.<\/jats:p>","DOI":"10.3390\/ijgi14120461","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T14:59:04Z","timestamp":1763996344000},"page":"461","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Agent Deep Reinforcement Learning Method with Diversified Policies for Continuous Location of Express Delivery Stations Under Heterogeneous Scenarios"],"prefix":"10.3390","volume":"14","author":[{"given":"Yijie","family":"Lyu","sequence":"first","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410083, China"}]},{"given":"Zhongan","family":"Tang","sequence":"additional","affiliation":[{"name":"The Third Surveying and Mapping Institute of Hunan Province, Changsha 410018, China"},{"name":"Hunan Geospatial Information Engineering and Technology Research Center, Changsha 410018, China"}]},{"given":"Yalun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410083, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1151-4309","authenticated-orcid":false,"given":"Baoju","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410083, China"},{"name":"The Third Surveying and Mapping Institute of Hunan Province, Changsha 410018, China"}]},{"given":"Min","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410083, China"},{"name":"The Third Surveying and Mapping Institute of Hunan Province, Changsha 410018, China"}]},{"given":"Guohua","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha 410083, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"ref_1","unstructured":"Ministry of Commerce of the People\u2019s Republic of China (2025, October 31). China E-Commerce Report 2022, Available online: https:\/\/dzsws.mofcom.gov.cn\/zthd\/ndbg\/art\/2023\/art_21d89f715e43476eae4c420a9d787d41.html."},{"key":"ref_2","first-page":"1239","article-title":"Sustainability benchmarking for logistics center location decision: An example from an emerging country","volume":"31","year":"2020","journal-title":"Manag. Environ. Qual."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhao, X. (2014, January 24\u201326). Based on gravity method of logistics distribution center location strategy research. Proceedings of the International Conference on Logistics Engineering, Management and Computer Science, Shenyang, China.","DOI":"10.2991\/lemcs-14.2014.134"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"104085","DOI":"10.1016\/j.rineng.2025.104085","article-title":"Last-mile logistics with alternative delivery locations: A systematic literature review","volume":"25","author":"Pourmohammadreza","year":"2025","journal-title":"Results Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1040","DOI":"10.1016\/j.ejor.2022.10.037","article-title":"Multi-type maximal covering location problems: Hybridizing discrete and continuous problems","volume":"307","author":"Blanco","year":"2023","journal-title":"Eur. J. Oper. Res."},{"key":"ref_6","first-page":"429","article-title":"A two-echelon location routing problem with mobile satellites for last-mile delivery: Mathematical formulation and clustering-based heuristic method","volume":"332","author":"Sutrisno","year":"2024","journal-title":"Ann. Oper. Res."},{"key":"ref_7","unstructured":"Su, H., Zheng, Y., Ding, J., Jin, D., and Li, Y. (November, January 29). Large-scale urban facility location selection with knowledge-informed reinforcement learning. Proceedings of the 32nd ACM International Conference on Advanced Geographic Information Systems (SIGSPATIAL \u201824), Atlanta, GA, USA."},{"key":"ref_8","first-page":"104454","article-title":"AIAM: Adaptive interactive attention model for solving p-Median problem via deep reinforcement learning","volume":"138","author":"Liang","year":"2025","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"103872","DOI":"10.1016\/j.tre.2024.103872","article-title":"Strategic planning of geo-fenced micro-mobility facilities using reinforcement learning","volume":"194","author":"Teusch","year":"2025","journal-title":"Transp. Res. Part E Logist. Transp. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2722","DOI":"10.1111\/tgis.13252","article-title":"A multi-objective optimization method for shelter site selection based on deep reinforcement learning","volume":"28","author":"Zhang","year":"2024","journal-title":"Trans. GIS"},{"key":"ref_11","first-page":"103710","article-title":"ReCovNet: Reinforcement learning with covering information for solving maximal coverage billboards location problem","volume":"128","author":"Zhong","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1287\/opre.19.6.1363","article-title":"The location of emergency service facilities","volume":"19","author":"Toregas","year":"1971","journal-title":"Oper. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1111\/j.1435-5597.1974.tb00902.x","article-title":"The maximal covering location problem","volume":"32","author":"Church","year":"1974","journal-title":"Pap. Reg. Sci. Assoc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1111\/j.1538-4632.2004.tb01140.x","article-title":"Aggregation decomposition and aggregation guidelines for a class of minimax and covering location models","volume":"36","author":"Francis","year":"2004","journal-title":"Geogr. Anal."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s10479-005-2044-2","article-title":"Demand point aggregation for planar covering location models","volume":"136","author":"Francis","year":"2005","journal-title":"Ann. Oper. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105310","DOI":"10.1016\/j.cor.2021.105310","article-title":"Continuous maximal covering location problems with interconnected facilities","volume":"132","author":"Blanco","year":"2021","journal-title":"Comput. Oper. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2062","DOI":"10.1016\/j.cor.2013.02.023","article-title":"Branch-and-bound algorithm for a competitive facility location problem","volume":"40","author":"Beresnev","year":"2013","journal-title":"Comput. Oper. Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"111150","DOI":"10.1016\/j.cie.2025.111150","article-title":"A dynamic programming-based computational intelligence method for optimal pickup and delivery in inter-terminal logistics","volume":"206","author":"Feng","year":"2025","journal-title":"Comput. Ind. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1080\/15472450.2022.2157211","article-title":"Optimizing the ground intra-city express delivery network: An integrated multiple centrality assessment, multi-criteria decision-making, and multi-objective integer programming model","volume":"28","author":"Liu","year":"2024","journal-title":"J. Intell. Transp. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"125924","DOI":"10.1016\/j.jenvman.2025.125924","article-title":"A low carbon multi-modal logistics network optimization: A novel neutrosophic mixed integer linear programming approach","volume":"387","author":"Kumar","year":"2025","journal-title":"J. Environ. Manag."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Frenk, H., Roos, K., Terlaky, T., and Zhang, S. (2000). The Mosek interior point optimizer for linear programming: An implementation of the homogeneous algorithm. High Performance Optimization, Springer.","DOI":"10.1007\/978-1-4757-3216-0"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kizhakkan, A.R., Rathore, A.K., and Awasthi, A. (2019, January 17\u201319). Review of electric vehicle charging station location planning. Proceedings of the IEEE Transportation Electrification Conference (ITEC-India), Bengaluru, India.","DOI":"10.1109\/ITEC-India48457.2019.ITECINDIA2019-226"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"24","DOI":"10.18757\/ejtir.2023.23.2.6786","article-title":"Locating Automated Parcel Lockers (APL) with known customers\u2019 demand: A mixed approach proposal","volume":"23","author":"Ottaviani","year":"2023","journal-title":"Eur. J. Transp. Infrastruct. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"103875","DOI":"10.1016\/j.jtrangeo.2024.103875","article-title":"Determining the number and location of micro-consolidation centres as a solution to growing e-commerce demand","volume":"117","author":"Kahalimoghadam","year":"2024","journal-title":"J. Transp. Geogr."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"109858","DOI":"10.1016\/j.cie.2023.109858","article-title":"Multi-neighborhood simulated annealing for the capacitated facility location problem with customer incompatibilities","volume":"188","author":"Ceschia","year":"2024","journal-title":"Comput. Ind. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"954","DOI":"10.1016\/j.ejor.2023.07.015","article-title":"A heuristic approach to the stochastic capacitated single allocation hub location problem with Bernoulli demands","volume":"312","author":"Andaryan","year":"2024","journal-title":"Eur. J. Oper. Res."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"128392","DOI":"10.1016\/j.physa.2022.128392","article-title":"A distribution center location optimization model based on minimizing operating costs under uncertain demand with logistics node capacity scalability","volume":"610","author":"Cui","year":"2023","journal-title":"Phys. A Stat. Mech. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1080\/19427867.2023.2277013","article-title":"Parcel locker location problem with selectable volume sizes and heterogeneous customers in the last mile delivery","volume":"16","author":"Zhou","year":"2024","journal-title":"Transp. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1016\/j.ejor.2020.08.018","article-title":"Heuristics for the dynamic facility location problem with modular capacities","volume":"290","author":"Silva","year":"2021","journal-title":"Eur. J. Oper. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1038\/s43588-023-00503-5","article-title":"Spatial planning of urban communities via deep reinforcement learning","volume":"3","author":"Zheng","year":"2023","journal-title":"Nat. Comput. Sci."},{"key":"ref_31","first-page":"103832","article-title":"Revisiting spatial optimization in the era of geospatial big data and GeoAI","volume":"129","author":"Cao","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s43762-024-00127-z","article-title":"A survey on applications of reinforcement learning in spatial resource allocation","volume":"4","author":"Zhang","year":"2024","journal-title":"Comput. Urban Sci."},{"key":"ref_33","unstructured":"Wang, S., Liang, H., Zhong, Y., Zhang, X., and Su, C. (2023, January 5\u20136). DeepMCLP: Solving the MCLP with Deep Reinforcement Learning for Urban Spatial Computing. Proceedings of the Spatial Data Science Symposium 2023, New York, NY, USA."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Gopi, S.P., and Magarini, M. (2021). Reinforcement learning aided UAV base station location optimization for rate maximization. Electronics, 10.","DOI":"10.3390\/electronics10232953"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"111195","DOI":"10.1016\/j.cie.2025.111195","article-title":"Data-driven reinforcement learning-based optimization of shared warehouse storage locations","volume":"206","author":"Yang","year":"2025","journal-title":"Comput. Ind. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Volodymyr","year":"2015","journal-title":"Nature"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"110543","DOI":"10.1016\/j.asoc.2023.110543","article-title":"Deep reinforcement learning for optimal rescue path planning in uncertain and complex urban pluvial flood scenarios","volume":"144","author":"Li","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.mfglet.2023.09.007","article-title":"Deep reinforcement learning for layout planning\u2014An MDP-based approach for the facility layout problem","volume":"38","author":"Heinbach","year":"2023","journal-title":"Manuf. Lett."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2299211","DOI":"10.1080\/17538947.2023.2299211","article-title":"Sponet: Solve spatial optimization problem using deep reinforcement learning for urban spatial decision analysis","volume":"17","author":"Liang","year":"2024","journal-title":"Int. J. Digit. Earth"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1109\/LCSYS.2021.3070850","article-title":"Deep reinforcement learning-based effective coverage control with connectivity constraints","volume":"6","author":"Meng","year":"2021","journal-title":"IEEE Control Syst. Lett."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"8243","DOI":"10.1109\/TVT.2020.2997896","article-title":"Multiagent deep reinforcement learning for urban traffic light control in vehicular networks","volume":"69","author":"Wu","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_42","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. (2017). Proximal Policy Optimization Algorithms. arXiv."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/12\/461\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T05:15:41Z","timestamp":1764134141000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/12\/461"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":42,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["ijgi14120461"],"URL":"https:\/\/doi.org\/10.3390\/ijgi14120461","relation":{},"ISSN":["2220-9964"],"issn-type":[{"type":"electronic","value":"2220-9964"}],"subject":[],"published":{"date-parts":[[2025,11,24]]}}}