{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T03:12:36Z","timestamp":1788577956593,"version":"build-2803163510"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"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":[[2021,10,31]]},"DOI":"10.1109\/ieeeconf53345.2021.9723270","type":"proceedings-article","created":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T20:26:46Z","timestamp":1646425606000},"page":"340-344","source":"Crossref","is-referenced-by-count":7,"title":["Distributed Proximal Policy Optimization for Contention-Based Spectrum Access"],"prefix":"10.1109","author":[{"given":"Akash","family":"Doshi","sequence":"first","affiliation":[{"name":"University of Texas at Austin,Department of Electrical and Computer Engineering,TX,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey G.","family":"Andrews","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Electrical and Computer Engineering,TX,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2010.03.090802"},{"key":"ref13","article-title":"Deep Recurrent Q-learning for Partially Observable MDPs","author":"hausknecht","year":"2015","journal-title":"AAAI Fall Symposium Series"},{"key":"ref14","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Adv in Neural Info Proc Syst"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref16","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"Proc ICLR"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2005.1424480"},{"key":"ref3","article-title":"Broadband Radio Access Networks (BRAN); 5GHz high performance RLAN","year":"2014","journal-title":"European Telecommunications Standards Institute (ETSI) European Standards (EN) 301 893"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DYSPAN.2011.5936261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DySPAN.2019.8935859"},{"key":"ref2","article-title":"Study on NR-based access to unlicensed spectrum","year":"2018","journal-title":"3rd Generation Partnership Project (3GPP) Technical Report (TR) 38 801"},{"key":"ref1","article-title":"Feasibility Study on Licensed-Assisted Access to Unlicensed Spectrum","year":"2015","journal-title":"3rd Generation Partnership Project (3GPP) Technical report (TR) 36 814"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087254"},{"key":"ref20","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"2017","journal-title":"Adv in Neural Info Proc Syst"}],"event":{"name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2021,10,31]]},"end":{"date-parts":[[2021,11,3]]}},"container-title":["2021 55th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9723034\/9723086\/09723270.pdf?arnumber=9723270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,15]],"date-time":"2022-06-15T20:16:44Z","timestamp":1655324204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9723270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf53345.2021.9723270","relation":{},"subject":[],"published":{"date-parts":[[2021,10,31]]}}}