{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T04:11:24Z","timestamp":1746591084258,"version":"3.40.5"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T00:00:00Z","timestamp":1736467200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T00:00:00Z","timestamp":1736467200000},"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":[[2025,1,10]]},"DOI":"10.1109\/ccnc54725.2025.10976191","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:52:06Z","timestamp":1746467526000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["A Multi-Agent Reinforcement Learning Testbed for Cognitive Radio Applications"],"prefix":"10.1109","author":[{"given":"Sriniketh","family":"Vangaru","sequence":"first","affiliation":[{"name":"Virginia Tech National Security Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Rosen","sequence":"additional","affiliation":[{"name":"Virginia Tech National Security Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dylan","family":"Green","sequence":"additional","affiliation":[{"name":"Virginia Tech National Security Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raphael","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"Virginia Tech National Security Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maxwell","family":"Wiecek","sequence":"additional","affiliation":[{"name":"Virginia Tech National Security Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amos","family":"Johnson","sequence":"additional","affiliation":[{"name":"Morehouse College"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alyse M.","family":"Jones","sequence":"additional","affiliation":[{"name":"Virginia Tech National Security Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William C.","family":"Headley","sequence":"additional","affiliation":[{"name":"Virginia Tech National Security Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"FCC Table of Frequency Allocations","year":"2022","key":"ref1"},{"volume-title":"Spectrum Allocation in the United States","year":"2022","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2019.8917869"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IC_ASET49463.2020.9318287"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCChina.2016.7636793"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WOCN.2012.6331885"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1109\/ICMLA58977.2023.00046","article-title":"RFRL Gym: A Reinforcement Learning Testbed for Cognitive Radio Applications","volume-title":"2023 International Conference on Machine Learning and Applications (ICMLA)","author":"Rosen","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3303211"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2966271"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.130.2200390"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013763"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"ref13","first-page":"321","volume-title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","author":"Zhang","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44188-7_16"},{"key":"ref15","first-page":"2626","article-title":"Deep Learning based Wireless Channel Prediction: 5G Scenario","volume-title":"Procedia Computer Science","volume":"218","author":"Varshney","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3205184"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"101845","DOI":"10.1016\/j.phycom.2022.101845","article-title":"Dynamic Spectrum Access Based on Deep Reinforcement Learning for Multiple Access in Cognitive Radio","volume":"54","author":"Li","year":"2022","journal-title":"Physical Communication"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"102054","DOI":"10.1016\/j.phycom.2023.102054","article-title":"Distributed Dynamic Spectrum Access Through Multi-Agent Deep Recurrent Q-Learning in Cognitive Radio Network","volume":"58","author":"Giri","year":"2023","journal-title":"Physical Communication"},{"volume-title":"A Survey of Progress on Cooperative Multi-Agent Reinforcement Learning in Open Environment","year":"2023","author":"Yuan","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00175"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1016\/j.icte.2024.01.001","article-title":"Multi-Agent Reinforcement Learning Based Optimal Energy Sensing Threshold Control in Distributed Cognitive Radio Networks with Directional Antenna","author":"Pham","year":"2024","journal-title":"ICT Express"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3168296"},{"key":"ref23","first-page":"1","article-title":"GrGym: A Playground for Research on RL\/AI Enhanced Wireless Networks","volume-title":"European Wireless 2022; 27th European Wireless Conference","author":"Zubow","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3345768.3355908"},{"issue":"1","key":"ref25","first-page":"4","article-title":"Overview of the Colosseum: The World\u2019s Largest Test Bed for Radio Experiments","volume":"5","author":"Coleman","year":"2019","journal-title":"Johns Hopkins Applied Physics Laboratory Technical Digest"},{"volume-title":"OpenAI Gym","year":"2016","author":"Brockman","key":"ref26"},{"volume-title":"Stable-Baselines3 Docs - Reliable Reinforcement Learning Implementations","year":"2024","key":"ref27"},{"volume-title":"PettingZoo: An API Standard for Multi-Agent Reinforcement Learning","year":"2023","key":"ref28"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"109502","DOI":"10.1016\/j.comnet.2022.109502","article-title":"OpenRAN Gym: AI\/ML Development, Data Collection, and Testing for O-RAN on PAWR Platforms","volume":"220","author":"Bonati","year":"2023","journal-title":"Computer Networks"},{"volume-title":"Gymnasium: An API Standard for Reinforcement Learning with a Diverse Collection of Reference Environments","year":"2023","author":"Foundation","key":"ref30"},{"volume-title":"RLlib: Industry-Grade Reinforcement Learning","year":"2023","key":"ref31"},{"key":"ref32","first-page":"844","article-title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","volume-title":"Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems","author":"Lyu","year":"2021"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1016\/j.jai.2024.02.003","article-title":"A Survey on Multi-Agent Reinforcement Learning and Its Application","author":"Ning","year":"2024","journal-title":"Journal of Automation and Intelligence"},{"issue":"4","key":"ref34","doi-asserted-by":"crossref","DOI":"10.1016\/j.xinn.2021.100162","article-title":"DTDE: A New Cooperative Multi-Agent Reinforcement Learning Framework","volume":"2","author":"Wen","year":"2021","journal-title":"The Innovation"},{"volume-title":"Playing Atari with Deep Reinforcement Learning","year":"2013","author":"Mnih","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3508546.3508598"},{"volume-title":"Proximal Policy Optimization Algorithms","year":"2017","author":"Schulman","key":"ref37"},{"volume-title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","year":"2018","author":"Espeholt","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref40","first-page":"2497","article-title":"Continual Reinforcement Learning with Complex Synapses","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Kaplanis","year":"2016"}],"event":{"name":"2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC)","start":{"date-parts":[[2025,1,10]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2025,1,13]]}},"container-title":["2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10975854\/10975830\/10976191.pdf?arnumber=10976191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T04:51:54Z","timestamp":1746507114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10976191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,10]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ccnc54725.2025.10976191","relation":{},"subject":[],"published":{"date-parts":[[2025,1,10]]}}}