{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:18:37Z","timestamp":1774455517550,"version":"3.50.1"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,10]],"date-time":"2022-04-10T00:00:00Z","timestamp":1649548800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,10]],"date-time":"2022-04-10T00:00:00Z","timestamp":1649548800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,10]]},"DOI":"10.1109\/wcnc51071.2022.9771605","type":"proceedings-article","created":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:45:39Z","timestamp":1652733939000},"page":"1461-1466","source":"Crossref","is-referenced-by-count":21,"title":["On-Policy vs. Off-Policy Deep Reinforcement Learning for Resource Allocation in Open Radio Access Network"],"prefix":"10.1109","author":[{"given":"Nessrine","family":"Hammami","sequence":"first","affiliation":[{"name":"University of Quebec,École de Technologie Supérieure (ÉTS),Canada"}]},{"given":"Kim Khoa","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Quebec,École de Technologie Supérieure (ÉTS),Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","author":"Gu","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997286"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933893"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3081694"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.107904"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2021.3073744"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3090513"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3026354"},{"key":"ref10","article-title":"ORAN-WG2.AIML.v01.00: O-RAN Working Group 2 AI\/ML workflow description and requirements","year":"2019","journal-title":"Technical Report"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.123"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2881964"},{"key":"ref13","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref14","article-title":"Sample efficient actor-critic with experience replay","author":"Wang","year":"2017"},{"key":"ref15","article-title":"Alibaba production cluster data v2018","year":"2018"},{"key":"ref16","article-title":"On-policy vs. off-policy deep reinforcement learning for resource allocation in open radio access network","author":"Hammami","year":"2021"}],"event":{"name":"2022 IEEE Wireless Communications and Networking Conference (WCNC)","location":"Austin, TX, USA","start":{"date-parts":[[2022,4,10]]},"end":{"date-parts":[[2022,4,13]]}},"container-title":["2022 IEEE Wireless Communications and Networking Conference (WCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9771381\/9771540\/09771605.pdf?arnumber=9771605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T02:55:14Z","timestamp":1706064914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9771605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,10]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/wcnc51071.2022.9771605","relation":{},"subject":[],"published":{"date-parts":[[2022,4,10]]}}}