{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:08:05Z","timestamp":1783526885868,"version":"3.55.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"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":[],"published-print":{"date-parts":[[2024,9,2]]},"DOI":"10.1109\/pimrc59610.2024.10817242","type":"proceedings-article","created":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T19:22:36Z","timestamp":1735759356000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Agent Proximal Policy Optimization for Dynamic Multi-Channel URLLC Access"],"prefix":"10.1109","author":[{"given":"Beno\u00eet-Marie","family":"Robaglia","sequence":"first","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Telecom Paris"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marceau","family":"Coupechoux","sequence":"additional","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Telecom Paris"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Tsilimantos","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd,Advanced Wireless Technology Lab, Paris Research Center"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"52065394","article-title":"Ultra-reliable low-latency 5 g for industrial automation","volume-title":"Technol. Rep. Qualcomm","volume":"2","author":"Brown","year":"2018"},{"key":"ref2","volume-title":"Study on scenarios and requirements for next generation access technologies"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2018.2884445"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975545"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2952909"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2980861"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3126112"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3099495"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3168296"},{"key":"ref12","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"International conference on machine learning.","author":"Duan"},{"key":"ref13","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"arXiv preprint arXiv:2011.09533"},{"key":"ref14","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","author":"Kuba","year":"2021","journal-title":"arXiv preprint arXiv:2109.11251"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2100136"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2200\/s00507ed1v01y201305cnt014"},{"key":"ref18","volume-title":"Feasibility Study on Licensed-Assisted Access to Unlicensed Spectrum"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1960.tb03959.x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_15"},{"key":"ref21","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning.","author":"Schulman"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref23","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv preprint arXiv:1506.02438"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref25","article-title":"Deep Recurrent Q-learning for Partially Observable MDPs","volume-title":"AAAI Fall Symposeum","author":"Hausknecht"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref27","volume-title":"Study on physical layer enhancements for NR ultrareliable and low latency case (URLLC)"},{"key":"ref28","volume-title":"NR; Physical channels and modulation"}],"event":{"name":"2024 IEEE 35th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","location":"Valencia, Spain","start":{"date-parts":[[2024,9,2]]},"end":{"date-parts":[[2024,9,5]]}},"container-title":["2024 IEEE 35th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10817155\/10817156\/10817242.pdf?arnumber=10817242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T05:48:40Z","timestamp":1735796920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10817242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/pimrc59610.2024.10817242","relation":{},"subject":[],"published":{"date-parts":[[2024,9,2]]}}}