{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:51:54Z","timestamp":1774021914699,"version":"3.50.1"},"reference-count":15,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Netw. Lett."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/lnet.2023.3264486","type":"journal-article","created":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T17:50:43Z","timestamp":1680717043000},"page":"86-90","source":"Crossref","is-referenced-by-count":3,"title":["Fast Link Scheduling in Wireless Networks Using Regularized Off-Policy Reinforcement Learning"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0385-1225","authenticated-orcid":false,"given":"Sagnik","family":"Bhattacharya","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, IIT Kanpur, Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5934-667X","authenticated-orcid":false,"given":"Ayan","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, IIT Kanpur, Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subrahmanya Swamy","family":"Peruru","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, IIT Kanpur, Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kothapalli Venkata","family":"Srinivas","sequence":"additional","affiliation":[{"name":"Motorola Mobility, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2582785"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2417861"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414098"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975499.12"},{"key":"ref5","volume-title":"Gurobi optimizer reference manual","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/opre.42.5.860"},{"key":"ref7","first-page":"134","article-title":"Learning what to defer for maximum independent sets","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Ahn"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref9","first-page":"1","article-title":"On-policy vs. off-policy updates for deep reinforcement learning","volume-title":"Proc. Deep Reinforcement Learn. Front. Challenges IJCAI Workshop","author":"Hausknecht"},{"key":"ref10","first-page":"4214","article-title":"Muesli: Combining improvements in policy optimization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Hessel"},{"key":"ref11","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn., (ICML)","volume":"80","author":"Fujimoto"},{"key":"ref12","first-page":"6351","article-title":"Learning combinatorial optimization algorithms over graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6567069"},{"key":"ref14","first-page":"1","article-title":"Maximum a posteriori policy optimisation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Abdolmaleki"},{"key":"ref15","first-page":"537","article-title":"Combinatorial optimization with graph convolutional networks and guided tree search","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Li"}],"container-title":["IEEE Networking Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8253410\/10147268\/10092874.pdf?arnumber=10092874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T21:39:07Z","timestamp":1709242747000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10092874\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":15,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lnet.2023.3264486","relation":{},"ISSN":["2576-3156"],"issn-type":[{"value":"2576-3156","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}