{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T18:58:30Z","timestamp":1794077910893,"version":"4.8.0"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T00:00:00Z","timestamp":1644883200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T00:00:00Z","timestamp":1644883200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T00:00:00Z","timestamp":1644883200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1807600"],"award-info":[{"award-number":["2020YFB1807600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2022,2,15]]},"DOI":"10.1109\/jiot.2021.3094651","type":"journal-article","created":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T15:28:37Z","timestamp":1625585317000},"page":"2933-2943","source":"Crossref","is-referenced-by-count":113,"title":["Resource Allocation and Trajectory Design in UAV-Aided Cellular Networks Based on Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3427-5040","authenticated-orcid":false,"given":"Sixing","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1006-7594","authenticated-orcid":false,"given":"F. Richard","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/AERO.2014.6836448"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.7470933"},{"key":"ref3","article-title":"Study on new radio (NR) to support non-terrestrial networks","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2612119"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2874531"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2840143"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2926279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2018.2880467"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2951770"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2880468"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946153"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2899208"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2911294"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref15","volume-title":"Parametrized deep Q-networks learning: Reinforcement learning with discrete-continuous hybrid action space","author":"Xiong","year":"2018"},{"key":"ref16","volume-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2544866"},{"key":"ref19","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst. (AAMAS)","author":"Sunehag"},{"key":"ref20","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Son"},{"key":"ref21","volume-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020"},{"key":"ref22","volume-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"Wang","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2611512"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9704905\/09475535.pdf?arnumber=9475535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T19:01:44Z","timestamp":1704999704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9475535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,15]]},"references-count":23,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2021.3094651","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,15]]}}}