{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T17:54:40Z","timestamp":1770054880137,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":10,"publisher":"ACM","funder":[{"name":"Shenzhen Fundamental Research Project","award":["JCYJ20220818103413029"],"award-info":[{"award-number":["JCYJ20220818103413029"]}]},{"name":"Low-Altitude Airspace Strategic Program Portfolio","award":["Z25306105"],"award-info":[{"award-number":["Z25306105"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,12]]},"DOI":"10.1145\/3784833.3784837","type":"proceedings-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T05:22:31Z","timestamp":1770009751000},"page":"237-243","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Dual-Branch Deep Deterministic Policy Gradient-Based Approach for Joint Task Orchestration and Channel Allocation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3782-9587","authenticated-orcid":false,"given":"Ji","family":"Li","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Beihang University, Beijing, China"},{"name":"National Superior College for Engineers, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2484-5080","authenticated-orcid":false,"given":"Rongke","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beihang University, Beijing, China"},{"name":"Shenzhen Institute of Beihang University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5834-2271","authenticated-orcid":false,"given":"Ling","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9055-7037","authenticated-orcid":false,"given":"Shaopeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"China Satellite Network Application Co.,Ltd China Satellite Network Group Co., Ltd, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5575-7181","authenticated-orcid":false,"given":"Haiyao","family":"Xie","sequence":"additional","affiliation":[{"name":"China Satellite Network Application Co.,Ltd China Satellite Network Group Co., Ltd, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2]]},"reference":[{"key":"e_1_3_3_1_1_2","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.7666\/d.D550014"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.3969\/j.issn.1003-0530.2014.03.001"},{"key":"e_1_3_3_1_4_2","volume-title":"Machine learning","author":"Watkins C J C H","year":"1992","unstructured":"Watkins C J C H, Dayan P. Q-learning[J]. Machine learning, 1992, 8(3-4): 279-292."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_3_1_6_2","volume-title":"ICLR","author":"Lillicrap T P","year":"2016","unstructured":"Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous Control with Deep Reinforcement Learning[C]. ICLR, 2016"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"e_1_3_3_1_8_2","first-page":"1057","article-title":"Policygradient methods forreinforcement learning with function approximation[J]","volume":"12","author":"SuRon R","year":"1999","unstructured":"SuRon R, Policygradient methods forreinforcement learning with function approximation[J]. Neural InformationProcessingSystems, 1999, 12:1057-10630","journal-title":"Neural InformationProcessingSystems"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"issue":"6","key":"e_1_3_3_1_10_2","first-page":"187","article-title":"Continuous control with deep reinforcement learning[J]","volume":"8","author":"Lillicrap T P","year":"2015","unstructured":"Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous control with deep reinforcement learning[J]. Computer Science, 2015, 8(6):187","journal-title":"Computer Science"}],"event":{"name":"ICCIP 2025: 2025 the 11th International Conference on Communication and Information Processing","location":"Lingshui Hainan China","acronym":"ICCIP 2025"},"container-title":["Proceedings of the 2025 11th International Conference on Communication and Information Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3784833.3784837","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T07:48:09Z","timestamp":1770018489000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3784833.3784837"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":10,"alternative-id":["10.1145\/3784833.3784837","10.1145\/3784833"],"URL":"https:\/\/doi.org\/10.1145\/3784833.3784837","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]},"assertion":[{"value":"2026-02-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}