{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:13:26Z","timestamp":1763644406393,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T00:00:00Z","timestamp":1717891200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T00:00:00Z","timestamp":1717891200000},"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":[[2024,6,9]]},"DOI":"10.1109\/icc51166.2024.10622210","type":"proceedings-article","created":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T15:34:42Z","timestamp":1724168082000},"page":"5571-5576","source":"Crossref","is-referenced-by-count":1,"title":["Over-the-air Federated Policy Gradient"],"prefix":"10.1109","author":[{"given":"Huiwen","family":"Yang","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingying","family":"Huang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhrakanti","family":"Dey","sequence":"additional","affiliation":[{"name":"Uppsala University,Uppsala,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Shi","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref2","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Richard","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Actor-critic algorithms","volume":"12","author":"Konda","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref5","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"A survey of deep reinforcement learning in video games","author":"Shao","year":"2019","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref9","first-page":"4026","article-title":"Stochastic variance-reduced policy gradient","volume-title":"International conference on machine learning","author":"Papini"},{"key":"ref10","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning","author":"Silver"},{"key":"ref11","article-title":"Continuous control with deep reinforcement learning","author":"Timothy","year":"2015","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/AIKE.2019.00031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3081626"},{"key":"ref15","first-page":"10997","article-title":"Federated reinforcement learning: Linear speedup under markovian sampling","volume-title":"International Conference on Machine Learning","author":"Khodadadian"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3078100"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2961673"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2974748"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3039309"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2914046"},{"key":"ref21","article-title":"Over-the-air multi-view pooling for distributed sensing","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2021.3133525"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.011.2000467"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3130993"},{"journal-title":"Over-the-air federated td learning","year":"2023","author":"Dal Fabbro","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2989580"},{"key":"ref27","article-title":"Over-the-air federated policy gradient","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Distributed policy gradient with variance reduction in multi-agent reinforcement learning","author":"Zhao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3279268"},{"key":"ref30","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"Mordatch","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"ICC 2024 - IEEE International Conference on Communications","start":{"date-parts":[[2024,6,9]]},"location":"Denver, CO, USA","end":{"date-parts":[[2024,6,13]]}},"container-title":["ICC 2024 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10622104\/10622158\/10622210.pdf?arnumber=10622210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T20:29:29Z","timestamp":1724963369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10622210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,9]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icc51166.2024.10622210","relation":{},"subject":[],"published":{"date-parts":[[2024,6,9]]}}}