{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T04:09:45Z","timestamp":1777349385128,"version":"3.51.4"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2024.3411073","type":"journal-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T13:31:47Z","timestamp":1717767107000},"page":"178540-178555","source":"Crossref","is-referenced-by-count":1,"title":["Bounded Low Latency via Inverse Reinforcement Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0633-404X","authenticated-orcid":false,"given":"Hossein","family":"Shafieirad","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0224-2209","authenticated-orcid":false,"given":"Raviraj S.","family":"Adve","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1260-2853","authenticated-orcid":false,"given":"Akram Bin","family":"Sediq","sequence":"additional","affiliation":[{"name":"Ericsson, Ottawa, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9785-3530","authenticated-orcid":false,"given":"Hamza U.","family":"Sokun","sequence":"additional","affiliation":[{"name":"Ericsson, Ottawa, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/ett.4394"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3004232"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3020645"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2786343"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117163"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054840"},{"key":"ref7","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. 17th Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3206035"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685672"},{"key":"ref11","article-title":"On meeting a maximum delay constraint using reinforcement learning in wireless networks","author":"Shafieirad"},{"key":"ref12","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI","author":"Ziebart"},{"key":"ref13","first-page":"1","article-title":"Nonlinear inverse reinforcement learning with Gaussian processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Levine"},{"key":"ref14","first-page":"1","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref15","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013221"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/s23031383"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10108-x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2799203"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5220\/0006908602020210"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2019.2924242"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160449"},{"key":"ref23","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Brown"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1201\/9780203489802"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref27","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00026"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10551844.pdf?arnumber=10551844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T05:38:00Z","timestamp":1761025080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10551844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3411073","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}