{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T21:17:21Z","timestamp":1762377441145,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"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":["IEEE Internet Things J."],"published-print":{"date-parts":[[2024,3,1]]},"DOI":"10.1109\/jiot.2023.3316078","type":"journal-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:44:36Z","timestamp":1694799876000},"page":"7710-7723","source":"Crossref","is-referenced-by-count":4,"title":["Blockchain-Assisted Demonstration Cloning for Multiagent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9275-2677","authenticated-orcid":false,"given":"Ahmed","family":"Alagha","sequence":"first","affiliation":[{"name":"Concordia Institute for Information Systems Engineering, Concordia University, Montreal, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3136-4849","authenticated-orcid":false,"given":"Jamal","family":"Bentahar","sequence":"additional","affiliation":[{"name":"Concordia Institute for Information Systems Engineering, Concordia University, Montreal, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9574-5384","authenticated-orcid":false,"given":"Hadi","family":"Otrok","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science and the Center of Cyber Physical Systems, Khalifa University, Abu Dhabi, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8412-5622","authenticated-orcid":false,"given":"Shakti","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science and the Center of Cyber Physical Systems, Khalifa University, Abu Dhabi, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6915-3759","authenticated-orcid":false,"given":"Rabeb","family":"Mizouni","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science and the Center of Cyber Physical Systems, Khalifa University, Abu Dhabi, UAE"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2021.102227"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2022.102927"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3196049"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref5","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.06.015"},{"key":"ref8","first-page":"1007","article-title":"Fault-tolerant federated reinforcement learning with theoretical guarantee","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3086910"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/AIKE.2019.00031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref12","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.06.050"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119481"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3075439"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref19","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv:1707.08817"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3072611"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3203850"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3078514"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800286"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3026589"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931179"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-11748-0_15"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/s19040960"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3262663"},{"key":"ref29","first-page":"1","article-title":"Emergent tool use from multi-agent autocurricula","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Baker"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062803"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref35","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Schulman"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2011.12.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3217689"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.05.025"},{"key":"ref39","article-title":"IPFS\u2014Content addressed, versioned, P2P file system","author":"Benet","year":"2014","journal-title":"arXiv:1407.3561"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2019.2907059"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107144"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2015.06.006"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574714002872"},{"key":"ref44","first-page":"1","article-title":"Autonomous vehicle fleet coordination with deep reinforcement learning","volume-title":"Proc. ICLR","author":"Punma"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3412841.3441953"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2894956"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2023.100867"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2023.100744"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2020.102783"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2020.102968"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3188557"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2023.103601"},{"volume-title":"LeNet-5, convolutional neural networks","year":"2015","author":"LeCun","key":"ref53"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10443092\/10251952.pdf?arnumber=10251952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T01:57:39Z","timestamp":1709344659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10251952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,1]]},"references-count":53,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3316078","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"type":"electronic","value":"2327-4662"},{"type":"electronic","value":"2372-2541"}],"subject":[],"published":{"date-parts":[[2024,3,1]]}}}