{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:17:33Z","timestamp":1740133053333,"version":"3.37.3"},"reference-count":11,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1804800"],"award-info":[{"award-number":["2020YFB1804800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National NSF of China","doi-asserted-by":"publisher","award":["61731002","62071425"],"award-info":[{"award-number":["61731002","62071425"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Key R&D Plan","award":["2019C01002","2019C03131"],"award-info":[{"award-number":["2019C01002","2019C03131"]}]},{"name":"Huawei Cooperation Project, and the Zhejiang Provincial NSF of China","award":["LY20F010016"],"award-info":[{"award-number":["LY20F010016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Lett."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/lcomm.2022.3144451","type":"journal-article","created":{"date-parts":[[2022,1,18]],"date-time":"2022-01-18T21:59:06Z","timestamp":1642543146000},"page":"823-827","source":"Crossref","is-referenced-by-count":4,"title":["Trustable Policy Collaboration Scheme for Multi-Agent Stigmergic Reinforcement Learning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4564-470X","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-5060","authenticated-orcid":false,"given":"Rongpeng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-7890","authenticated-orcid":false,"given":"Zhifeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang Laboratory, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1492-1364","authenticated-orcid":false,"given":"Honggang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056418"},{"key":"ref5","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref6","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"volume-title":"NNGeometry: Easy and Fast Fisher Information Matrices and Neural Tangent Kernels in PyTorch","year":"2021","author":"George","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3279268"},{"key":"ref10","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Vinitsky"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"}],"container-title":["IEEE Communications Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4234\/9751772\/09684873.pdf?arnumber=9684873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:07:09Z","timestamp":1705183629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9684873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":11,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lcomm.2022.3144451","relation":{},"ISSN":["1089-7798","1558-2558","2373-7891"],"issn-type":[{"type":"print","value":"1089-7798"},{"type":"electronic","value":"1558-2558"},{"type":"electronic","value":"2373-7891"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}