{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T15:10:54Z","timestamp":1772032254012,"version":"3.50.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003132","name":"Agentschap voor Innovatie door Wetenschap en Technologie","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1109\/jiot.2019.2955035","type":"journal-article","created":{"date-parts":[[2019,11,26]],"date-time":"2019-11-26T01:07:54Z","timestamp":1574730474000},"page":"1387-1400","source":"Crossref","is-referenced-by-count":22,"title":["Parallel Reinforcement Learning With Minimal Communication Overhead for IoT Environments"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8152-7143","authenticated-orcid":false,"given":"Miguel","family":"Camelo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maxim","family":"Claeys","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven","family":"Latre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","year":"2019","journal-title":"Teaching Intelligent Robots the Art of Delegation"},{"key":"ref38","year":"2019","journal-title":"The Sparki Robot"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref32","first-page":"9","article-title":"Coordinating hundreds of cooperative, autonomous vehicles in warehouses","volume":"29","author":"wurman","year":"2008","journal-title":"AI Mag"},{"key":"ref31","first-page":"631","article-title":"A parallel scheduling algorithm for reinforcement learning in large state space","volume":"6","author":"liu","year":"2012","journal-title":"Front Comput Sci"},{"key":"ref30","first-page":"11","article-title":"A parallel implementation of Q-learning based on communication with cache","volume":"1","author":"printista","year":"2002","journal-title":"J Comput Sci Technol"},{"key":"ref37","author":"bhuiyan","year":"2017","journal-title":"High Performance in-memory computing with apache Ignite"},{"key":"ref36","author":"macglashan","year":"2019","journal-title":"The Brown-UMBC Reinforcement Learning and Planning (BURLAP)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2007.4304002"},{"key":"ref34","article-title":"CAD2RL: Real single-image flight without a single real image","author":"sadeghi","year":"2016","journal-title":"arXiv preprint arXiv 1611 04201"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref11","first-page":"1","article-title":"Reinforcement learning algorithms for homogeneous multi-agent systems","author":"kretchmar","year":"2003","journal-title":"Proc Workshop Agent Swarm Program"},{"key":"ref12","first-page":"607","article-title":"A complexity analysis of cooperative mechanisms in reinforcement learning","author":"whitehead","year":"1991","journal-title":"Proc 9th Nat Conf Artificial Intell (AAAI-91)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC.2016.007"},{"key":"ref14","first-page":"1","article-title":"Parallel reinforcement learning with state action space partitioning","author":"mannion","year":"2015","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IAT.2006.3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v33i3.2426"},{"key":"ref17","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77002-2_47"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT.2016.7845391"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.05.172"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2759728"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2011.6181717"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2773600"},{"key":"ref29","first-page":"1","article-title":"Q-learning-based adaptive power management for IoT system-on-chips with embedded power states","author":"debizet","year":"2018","journal-title":"Proc IEEE Int Symp Circuits Syst (ISCAS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref7","first-page":"1054","author":"sutton","year":"2017","journal-title":"Reinforcement Learning An Introduction Reinforcement Learning Lectures"},{"key":"ref2","article-title":"Autonomous UAV navigation using reinforcement learning","author":"pham","year":"2018","journal-title":"arXiv preprint arXiv 1801 08639"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/j.2041-210X.2012.00242.x"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2444095"},{"key":"ref20","first-page":"114","article-title":"Parallel reinforcement learning","volume":"6","author":"kretchmar","year":"2002","journal-title":"Proc 6th World Conf Syst Cybern Informat"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2875926"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2712560"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2812210"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2014.2368356"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT.2018.8355169"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/8994209\/08911213.pdf?arnumber=8911213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:27:25Z","timestamp":1651080445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8911213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":39,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2019.2955035","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2]]}}}