{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:08Z","timestamp":1786120808079,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["U25A20436, 62372047, 62406029"],"award-info":[{"award-number":["U25A20436, 62372047, 62406029"]}]},{"name":"Guangxi Key Research \\& Development Program","award":["FN2504240036, 2025FN96441087"],"award-info":[{"award-number":["FN2504240036, 2025FN96441087"]}]},{"name":"Guangdong S&T Programme","award":["2025B0101120006"],"award-info":[{"award-number":["2025B0101120006"]}]},{"name":"the Supplemental Funds for Major Scientific Research Projects of Beijing Normal University, Zhuhai","award":["ZHPT2023002"],"award-info":[{"award-number":["ZHPT2023002"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["2025JKZG069"],"award-info":[{"award-number":["2025JKZG069"]}]},{"name":"Higher Education Research Topics of Guangdong Association of Higher Education in the 14th Five-Year Plan","award":["24GYB207"],"award-info":[{"award-number":["24GYB207"]}]},{"name":"Guangdong Provicial General Grant","award":["2026A1515010196"],"award-info":[{"award-number":["2026A1515010196"]}]},{"name":"AIRH, BNBU","award":["2020KSYS007"],"award-info":[{"award-number":["2020KSYS007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817998","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"3715-3726","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PG-DyRA: Potential-Game Guided Multi-Agent Collaboration for Dynamic Urban Resource Allocation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7533-3198","authenticated-orcid":false,"given":"Yaxin","family":"Mei","sequence":"first","affiliation":[{"name":"Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4045-6091","authenticated-orcid":false,"given":"Huiling","family":"Qin","sequence":"additional","affiliation":[{"name":"Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2481-5648","authenticated-orcid":false,"given":"Chenhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1000-3937","authenticated-orcid":false,"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4515-0080","authenticated-orcid":false,"given":"Yu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, China and Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4819-621X","authenticated-orcid":false,"given":"Tian","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TQE.2022.3187367"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3610242"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.05.007"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2813008"},{"key":"e_1_3_2_2_5_1","first-page":"34","volume-title":"Science","volume":"153","author":"Bellman Richard","year":"1966","unstructured":"Richard Bellman. 1966. Dynamic Programming. Science, Vol. 153, 3731 (1966), 34-37."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1763"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trip.2023.100895"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3025316"},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML '19","volume":"1546","author":"Das Abhishek","year":"2019","unstructured":"Abhishek Das, Th\u00e9ophile Gervet, Joshua Romoff, Dhruv Batra, Devi Parikh, Mike Rabbat, and Joelle Pineau. 2019. TarMAC: Targeted Multi-Agent Communication. In Proceedings of the 36th International Conference on Machine Learning (ICML '19, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, New York, NY, USA, 1538-1546."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3241286"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3141165"},{"key":"e_1_3_2_2_12_1","volume-title":"Reducibility Among Combinatorial Problems","author":"Karp Richard M.","unstructured":"Richard M. Karp. 2010. Reducibility Among Combinatorial Problems. Springer Berlin Heidelberg, Berlin, Heidelberg, 219-241."},{"key":"e_1_3_2_2_13_1","volume-title":"A Game-Theoretic Spatio-Temporal Reinforcement Learning Framework for Collaborative Public Resource Allocation. arXiv preprint arXiv:2510.26184","author":"Lei Songxin","year":"2025","unstructured":"Songxin Lei, Qiongyan Wang, Yanchen Zhu, Hanyu Yao, Sijie Ruan, Weilin Ruan, Yuyu Luo, Huaming Wu, and Yuxuan Liang. 2025. A Game-Theoretic Spatio-Temporal Reinforcement Learning Framework for Collaborative Public Resource Allocation. arXiv preprint arXiv:2510.26184 (2025)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1006\/game.1996.0044"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NeurIPS '21","volume":"19222","author":"Papoudakis Georgios","year":"2021","unstructured":"Georgios Papoudakis, Filippos Christianos, and Stefano Albrecht. 2021. Agent Modelling under Partial Observability for Deep Reinforcement Learning. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NeurIPS '21, Vol. 34), M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.). Curran Associates, Inc., Red Hook, NY, USA, 19210-19222."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3165965"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103852"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML '18","volume":"4304","author":"Rashid Tabish","year":"2018","unstructured":"Tabish Rashid, Mikayel Samvelyan, Christian Schroeder, Gregory Farquhar, Jakob Foerster, and Shimon Whiteson. 2018. QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. In Proceedings of the 35th International Conference on Machine Learning (ICML '18, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). PMLR, 4295-4304."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380986"},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (Washington DC, USA) (KDD '22)","author":"Eshkevari Soheil Sadeghi","year":"2022","unstructured":"Soheil Sadeghi Eshkevari, Xiaocheng Tang, Zhiwei Qin, Jinhan Mei, Cheng Zhang, Qianying Meng, and Jia Xu. 2022. Reinforcement Learning in the Wild: Scalable RL Dispatching Algorithm Deployed in Ridehailing Marketplace. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (Washington DC, USA) (KDD '22). Association for Computing Machinery, New York, NY, USA, 3838\u20133848."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEM.2020.3015775"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3303502"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157348"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467070"},{"key":"e_1_3_2_2_26_1","first-page":"3522","volume-title":"GCRL: Efficient Delivery Area Assignment for Last-mile Logistics with Group-based Cooperative Reinforcement Learning. In 2023 IEEE 39th International Conference on Data Engineering (ICDE '23)","author":"Wang Hai","year":"2023","unstructured":"Hai Wang, Shuai Wang, Yu Yang, and Desheng Zhang. 2023b. GCRL: Efficient Delivery Area Assignment for Last-mile Logistics with Group-based Cooperative Reinforcement Learning. In 2023 IEEE 39th International Conference on Data Engineering (ICDE '23). IEEE, 3522-3534."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672052"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709205"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474717.3483923"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3167485"},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Learning Representations (ICLR '22)","author":"Wang Yuanfei","year":"2022","unstructured":"Yuanfei Wang, fangwei zhong, Jing Xu, and Yizhou Wang. 2022. ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind. In International Conference on Learning Representations (ICLR '22)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119606475"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems (Neurips '20","volume":"10064","author":"Xu Jing","year":"2020","unstructured":"Jing Xu, Fangwei Zhong, and Yizhou Wang. 2020. Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Neurips '20, Vol. 33). Curran Associates, Inc., 10053-10064."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219824"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2020.3044566"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1787"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368297"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:16:06Z","timestamp":1786065366000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817998"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":37,"alternative-id":["10.1145\/3770855.3817998","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817998","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}