{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:14:26Z","timestamp":1782990866020,"version":"3.54.5"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Peter Wall Institute for Advanced Studies through a research grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2994600","type":"journal-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:02:10Z","timestamp":1589511730000},"page":"95208-95222","source":"Crossref","is-referenced-by-count":5,"title":["Using Deep Reinforcement Learning to Improve Sensor Selection in the Internet of Things"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6992-0452","authenticated-orcid":false,"given":"Hootan","family":"Rashtian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sathish","family":"Gopalakrishnan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s18113797"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/s19163512"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2898173"},{"key":"ref13","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2944463"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10922-015-9352-x"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD.2014.6846925"},{"key":"ref19","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ATNAC.2018.8615377"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64367-0_10"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2952447"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2012.280"},{"key":"ref7","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","article-title":"GA3C: GPU-based A3C for deep reinforcement learning","volume":"abs 1611 6256","author":"babaeizadeh","year":"2016","journal-title":"CoRR"},{"key":"ref9","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"Policy gradient methods for reinforcement learning with function approximation and action-dependent baselines","author":"thomas","year":"2017","journal-title":"arXiv 1706 06643"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1002\/env.1014","article-title":"Predicting intra-urban variation in air pollution concentrations with complex spatio-temporal dependencies","volume":"21","author":"szpiro","year":"2010","journal-title":"Environmetrics"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.05.529"},{"key":"ref26","first-page":"1655","article-title":"Deep spatio-temporal residual networks for citywide crowd flows prediction","author":"zhang","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052577"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09093816.pdf?arnumber=9093816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T21:16:27Z","timestamp":1722892587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2994600","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}