{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T10:34:24Z","timestamp":1778495664422,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"13","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF RTML","award":["CCF-1937403"],"award-info":[{"award-number":["CCF-1937403"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,7,1]]},"DOI":"10.1109\/jiot.2025.3553808","type":"journal-article","created":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:47:51Z","timestamp":1742604471000},"page":"23852-23865","source":"Crossref","is-referenced-by-count":33,"title":["Meta-ETI: Meta-Reinforcement Learning With Explicit Task Inference for AAV-IoT Coverage"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9900-0530","authenticated-orcid":false,"given":"Songjun","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rutgers University–New Brunswick, New Brunswick, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7524-9044","authenticated-orcid":false,"given":"Chuanneng","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rutgers University–New Brunswick, New Brunswick, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5365-509X","authenticated-orcid":false,"given":"Dario","family":"Pompili","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rutgers University–New Brunswick, New Brunswick, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3111024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3236801"},{"key":"ref7","article-title":"A study on overfitting in deep reinforcement learning","author":"Zhang","year":"2018","journal-title":"arXiv:1804.06893"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3353302"},{"key":"ref9","article-title":"A survey of meta-reinforcement learning","author":"Beck","year":"2023","journal-title":"arXiv:2301.08028"},{"key":"ref10","first-page":"26519","article-title":"On the effectiveness of fine-tuning versus meta-reinforcement learning","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","volume":"35","author":"Zhao"},{"key":"ref11","first-page":"1","article-title":"A meta-MDP approach to exploration for lifelong reinforcement learning","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","volume":"32","author":"Garcia"},{"key":"ref12","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref13","article-title":"Some considerations on learning to explore via meta-reinforcement learning","author":"Stadie","year":"2018","journal-title":"arXiv:1803.01118"},{"key":"ref14","first-page":"1","article-title":"Meta-gradient reinforcement learning","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","volume":"31","author":"Xu"},{"key":"ref15","article-title":"Learning to learn: Meta-critic networks for sample efficient learning","author":"Sung","year":"2017","journal-title":"arXiv:1706.09529"},{"key":"ref16","first-page":"1","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","volume":"31","author":"Gupta"},{"key":"ref17","article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref18","article-title":"Learning to reinforcement learn","author":"Wang","year":"2016","journal-title":"arXiv:1611.05763"},{"key":"ref19","article-title":"A simple neural attentive meta-learner","author":"Mishra","year":"2017","journal-title":"arXiv:1707.03141"},{"key":"ref20","article-title":"Meta-q-learning","author":"Fakoor","year":"2019","journal-title":"arXiv:1910.00125"},{"key":"ref21","article-title":"Recurrent model-free RL can be a strong baseline for many POMDPs","author":"Ni","year":"2021","journal-title":"arXiv:2110.05038"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.086"},{"key":"ref23","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3182908"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCS.2018.8689249"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9149258"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864373"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2908171"},{"key":"ref29","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref30","first-page":"1","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sohn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00270"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727309"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/s17091967"},{"key":"ref34","article-title":"Enhanced LTE support for aerial vehicles; (Release 15)","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.0001.1900021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2021.12.076"},{"key":"ref37","first-page":"1","article-title":"Scenario analysis of pedestrian flow in public spaces","volume-title":"Proc. 12th Swiss Transp. Res. Conf.","author":"Sahaleh"},{"key":"ref38","volume-title":"A quantitative measure of fairness and discrimination","author":"Jain","year":"1984"},{"key":"ref39","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref40","article-title":"Meta-learning with latent embedding optimization","author":"Rusu","year":"2018","journal-title":"arXiv:1807.05960"},{"key":"ref41","article-title":"VariBAD: A very good method for Bayes-adaptive deep RL via meta-learning","author":"Zintgraf","year":"2019","journal-title":"arXiv:1910.08348"},{"key":"ref42","first-page":"6925","article-title":"Decoupling exploration and exploitation for meta-reinforcement learning without sacrifices","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref43","article-title":"ProMP: Proximal meta-policy search","author":"Rothfuss","year":"2018","journal-title":"arXiv:1810.06784"},{"key":"ref44","volume-title":"Planet Dump","year":"2017"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6488907\/11045559\/10937077-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11045559\/10937077.pdf?arnumber=10937077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T07:09:54Z","timestamp":1750748994000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10937077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":44,"journal-issue":{"issue":"13"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3553808","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]}}}