{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:08:34Z","timestamp":1764842914510,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"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":[[2024,7,10]]},"DOI":"10.23919\/acc60939.2024.10644549","type":"proceedings-article","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:56:19Z","timestamp":1725558979000},"page":"33-38","source":"Crossref","is-referenced-by-count":9,"title":["Distributed Reinforcement Learning For Swarm Systems With Reward Machines"],"prefix":"10.23919","author":[{"given":"Shayan Meshkat","family":"Alsadat","sequence":"first","affiliation":[{"name":"School of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85281"}]},{"given":"Nasim","family":"Baharisangari","sequence":"additional","affiliation":[{"name":"School of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85281"}]},{"given":"Yash","family":"Paliwal","sequence":"additional","affiliation":[{"name":"School of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85281"}]},{"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85281"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3176797"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-013-9349-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.1254295"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-27705-6_6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3098059"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2010.11.023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2012.2183831"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377041"},{"key":"ref9","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Is centralized training with decentralized execution framework centralized enough for marl?","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Icarte","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191236"},{"key":"ref13","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Yang","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"issue":"54","key":"ref16","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"H\u00fcttenrauch","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","article-title":"Reward machines for cooperative multi-agent reinforcement learning","author":"Neary","year":"2020","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2924843"},{"key":"ref19","article-title":"Inverse reinforcement learning in swarm systems","author":"So\u0161i\u0107","year":"2016","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.874516"}],"event":{"name":"2024 American Control Conference (ACC)","start":{"date-parts":[[2024,7,10]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10644130\/10644150\/10644549.pdf?arnumber=10644549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T06:59:19Z","timestamp":1725692359000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10644549\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":20,"URL":"https:\/\/doi.org\/10.23919\/acc60939.2024.10644549","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]}}}