{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T04:51:57Z","timestamp":1776401517727,"version":"3.51.2"},"reference-count":26,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:00Z","timestamp":1775692800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Key Research and Development Program of Henan Province","award":["252102321109"],"award-info":[{"award-number":["252102321109"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>In the era of information explosion, the effective configuration of labels on maps is crucial for the rapid comprehension of information. The point-feature label placement problem, particularly in large-scale and high-density scenarios with spatial mutual-exclusion constraints, is a classic NP-hard discrete optimization challenge. Existing metaheuristic algorithms (e.g., Simulated Annealing and Genetic Algorithm) often struggle to achieve high-quality global layouts due to their propensity to become trapped in local optima, inefficient random point-selection processes, and inadequate modeling of the spatial mutual-exclusion and blocking constraints between labels. To address these limitations, this paper proposes a Progressive Reinforcement Learning (PRL) algorithm specifically tailored for the point-feature label placement problem. The algorithm models the label placement process as a sequential decision-making problem within the Reinforcement Learning framework, optimized through agent\u2013environment interaction. Its core design comprises the following: (1) a staircase-like policy learning mechanism that shifts from \u201cbroad exploration in the early stage to precise exploitation in the later stage\u201d to balance global search and local optimization; (2) a data mining-based Intelligent Action Screening (IAS) mechanism, which dynamically identifies and prioritizes \u201chigh-value action points\u201d critical for improving layout quality by constructing the \u201cContribution Decline Degree\u201d and \u201cContribution Support Degree\u201d metrics. Experiments on large-scale real-world POI datasets (10,000, 20,000, and 32,312 points) demonstrate that the proposed algorithm significantly outperforms 13 state-of-the-art comparative algorithms, including Simulated Annealing, Genetic Algorithm, Differential Evolution, POPMUSIC, and DBSCAN, in terms of both placement quality and the number of successfully placed labels. It exhibits remarkable adaptability and competitiveness in handling high-density and complex scenarios.<\/jats:p>","DOI":"10.3390\/ijgi15040162","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T07:55:12Z","timestamp":1775807712000},"page":"162","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Progressive Reinforcement Learning for Point-Feature Label Placement in Map Annotation"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2182-7819","authenticated-orcid":false,"given":"Wen","family":"Cao","sequence":"first","affiliation":[{"name":"Huanghe University of Science and Technology, Zhengzhou 450063, China"},{"name":"Zhengzhou Zhonghe Jing Xuan Information Technology Co., Ltd., Zhengzhou 450000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinbao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Geoscience and Technology, Zhengzhou University, Zhengzhou 450001, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7130-4752","authenticated-orcid":false,"given":"Runsheng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhengzhou Shengda University of Economics, Business & Management, Zhengzhou 451191, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqiu","family":"Ren","sequence":"additional","affiliation":[{"name":"61206 Troops, Beijing 100043, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Chen","sequence":"additional","affiliation":[{"name":"Huanghe University of Science and Technology, Zhengzhou 450063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1145\/212332.212334","article-title":"An empirical study of algorithms for point-feature label placement","volume":"14","author":"Christensen","year":"1995","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_2","first-page":"228","article-title":"Practical results using simulated annealing for point feature label placement","volume":"24","author":"Zoraster","year":"1997","journal-title":"Cartogr. Geogr. Inf. Sci."},{"key":"ref_3","unstructured":"Murty, K.G. (2003). Optimization Models for Decision Making: Volume 1, University of Michigan."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"159","DOI":"10.3390\/ijgi5090159","article-title":"A labeling model based on the region of movability for point-feature label placement","volume":"5","author":"Lin","year":"2016","journal-title":"ISPRS Int. J. Geo-Inf."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.cageo.2007.01.007","article-title":"A greedy randomized adaptive search procedure for the point-feature cartographic label placement","volume":"34","author":"Cravo","year":"2008","journal-title":"Comput. Geosci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1023\/A:1013720231747","article-title":"Tabu search heuristic for point-feature cartographic label placement","volume":"6","author":"Yamamoto","year":"2002","journal-title":"GeoInformatica"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1016\/j.ejor.2013.10.021","article-title":"A clustering search metaheuristic for the point-feature cartographic label placement problem","volume":"234","author":"Rabello","year":"2014","journal-title":"Eur. J. Oper. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1023\/A:1020809627892","article-title":"Using genetic algorithms for solving hard problems in GIS","volume":"6","author":"Thierens","year":"2002","journal-title":"GeoInformatica"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Lu, F., Deng, J., Li, S., Liu, Y., and Li, H. (2019). A hybrid of differential evolution and genetic algorithm for the multiple geographical feature label placement problem. ISPRS Int. J. Geo-Inf., 8.","DOI":"10.3390\/ijgi8050237"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"144085","DOI":"10.1109\/ACCESS.2021.3120289","article-title":"Multiple geographical feature label placement based on multiple candidate positions in two degrees of freedom space","volume":"9","author":"Deng","year":"2021","journal-title":"IEEE Access"},{"key":"ref_11","unstructured":"Li, J., and Zhu, Q. (2019). A genetic tabu search algorithm for point-feature label placement considering road influence. Surv. Mapp. Bull., 80\u201385. (In Chinese)."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1016\/j.ejor.2007.10.002","article-title":"POPMUSIC for the point feature label placement problem","volume":"192","author":"Alvim","year":"2009","journal-title":"Eur. J. Oper. Res."},{"key":"ref_13","first-page":"902","article-title":"Application of Ant Colony Algorithm Based on Clustering Grouping in Automatic Placement of Map Point Feature Labels","volume":"17","author":"Zhou","year":"2015","journal-title":"J. Geo-Inf. Sci."},{"key":"ref_14","first-page":"289","article-title":"An annotation configuration algorithm for point features considering spatial distribution and annotation correlation","volume":"51","author":"Cao","year":"2022","journal-title":"Acta Geod. Cartogr. Sin."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"12169","DOI":"10.3934\/mbe.2023542","article-title":"A point-feature label placement algorithm based on spatial data mining","volume":"20","author":"Cao","year":"2023","journal-title":"Math. Biosci. Eng."},{"key":"ref_16","first-page":"123","article-title":"An automated point-feature cartographic annotation model considering the constraint of road network","volume":"41","author":"Du","year":"2016","journal-title":"Sci. Surv. Mapp."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2164","DOI":"10.1016\/j.cor.2010.03.005","article-title":"A new mathematical model and a lagrangean decomposition for the point-feature cartographic label placement problem","volume":"37","author":"Mauri","year":"2010","journal-title":"Comput. Oper. Res."},{"key":"ref_18","first-page":"91","article-title":"Quantitative measurement of ambiguity in point-feature label placement","volume":"26","author":"Luo","year":"2003","journal-title":"J. East China Inst. Technol. (Nat. Sci. Ed.)"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1064","DOI":"10.1109\/TFUZZ.2020.3016225","article-title":"Improved artificial immune system algorithm for Type-2 fuzzy flexible job shop scheduling problem","volume":"29","author":"Li","year":"2021","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"ref_20","unstructured":"Gyenes, B., Franke, N., Becker, P., and Neumann, G. (2024, January 6\u20139). PointPatchRL\u2014Masked Reconstruction Improves Reinforcement Learning on Point Clouds. Proceedings of the 8th Conference on Robot Learning (CoRL), Munich, Germany."},{"key":"ref_21","unstructured":"Miao, C., Zhang, Y., Wu, T., Deng, F., and Chen, C. (November, January 29). Deep Reinforcement Learning for Multi-Period Facility Location: Pk-median Dynamic Location Problem. Proceedings of the 32nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Atlanta, GA, USA."},{"key":"ref_22","first-page":"104973","article-title":"Spatiotemporal crime prediction and fairness-constrained spatial optimization with deep reinforcement learning for patrol region design","volume":"145","author":"Liang","year":"2025","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_23","unstructured":"Immel, F., Pauls, J.H., Fehler, R., Bieder, F., Merkert, J., and Stiller, C. (2025). SDTagNet: Leveraging Text-Annotated Navigation Maps for Online HD Map Construction. arXiv."},{"key":"ref_24","first-page":"45","article-title":"Automatic Image Annotation for Mapped Features Detection","volume":"181","author":"Noize","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_25","first-page":"945","article-title":"Spatial planning of urban communities via deep reinforcement learning","volume":"3","author":"Liu","year":"2023","journal-title":"Nat. Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1007\/s10707-014-0214-6","article-title":"Improving label placement quality by considering basemap detail with a raster-based approach","volume":"19","author":"Rylov","year":"2015","journal-title":"GeoInformatica"}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/4\/162\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T04:11:37Z","timestamp":1776399097000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/4\/162"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,9]]},"references-count":26,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["ijgi15040162"],"URL":"https:\/\/doi.org\/10.3390\/ijgi15040162","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,9]]}}}