{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:04:34Z","timestamp":1740103474492,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,19]]},"DOI":"10.1109\/ict-dm62768.2024.10798952","type":"proceedings-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:26:46Z","timestamp":1734550006000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Towards Efficient Task Offloading in Disaster Areas: a Constrained RL-based Approach"],"prefix":"10.1109","author":[{"given":"Yupeng","family":"Wang","sequence":"first","affiliation":[{"name":"Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinbo","family":"He","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyong","family":"Shi","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weizhen","family":"Han","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2020.10.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3312220"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3014896"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3232495"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2990630"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23860\/diss-li-hepfeng-2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICSS55994.2022.00029"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3510513.3510534"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3357150.3357395"},{"key":"ref10","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proceedings of the 31st ACM Advances in Neural Information Processing Systems (NeurIPS)","author":"Lowe"},{"issue":"178","key":"ref11","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3416822"},{"key":"ref13","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Achiam"},{"key":"ref14","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proceedings of the Nineteenth International Conference on Machine Learning (ICML)","author":"Kakade"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981831"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488886"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3133480"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2017.2789288"},{"article-title":"Reward constrained policy optimization","year":"2018","author":"Tessler","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.molcel.2005.03.012"},{"article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","year":"2020","author":"De Witt","key":"ref21"}],"event":{"name":"2024 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)","start":{"date-parts":[[2024,11,19]]},"location":"Setif, Algeria","end":{"date-parts":[[2024,11,21]]}},"container-title":["2024 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10798920\/10798562\/10798952.pdf?arnumber=10798952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T19:17:31Z","timestamp":1734635851000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10798952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,19]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ict-dm62768.2024.10798952","relation":{},"subject":[],"published":{"date-parts":[[2024,11,19]]}}}