{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:09:42Z","timestamp":1781194182206,"version":"3.54.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"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":[[2019,4]]},"DOI":"10.1109\/codit.2019.8820368","type":"proceedings-article","created":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T01:09:32Z","timestamp":1567472972000},"page":"1876-1881","source":"Crossref","is-referenced-by-count":8,"title":["Deep Reinforcement Learning-based Continuous Control for Multicopter Systems"],"prefix":"10.1109","author":[{"given":"Anush","family":"Manukyan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miguel A.","family":"Olivares-Mendez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthieu","family":"Geist","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holger","family":"Voos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"63","article-title":"Dynamic Modeling and Control of Quad Rotor","volume":"5","author":"balasubramanian","year":"2013","journal-title":"International Journal of Engineering and Technology (IJET)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2016.7838739"},{"key":"ref12","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref13","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref14","author":"zamora","year":"2016","journal-title":"Extending the OpenAI Gym for Robotics a Toolkit for Reinforcement Learning using ROS and Gazebo"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26054-9_23"},{"key":"ref16","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref17","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref18","author":"nachum","year":"2017","journal-title":"Trust-PCL An off-policy trust region method for continuous control"},{"key":"ref19","author":"islam","year":"2017","journal-title":"Reproducibility of benchmarked deep reinforcement learning tasks for continuous control"},{"key":"ref28","year":"0","journal-title":"Video clip of the learning process"},{"key":"ref4","author":"koch","year":"2018","journal-title":"Reinforcement Learning for UAV Attitude Control"},{"key":"ref27","year":"0","journal-title":"RotorS MAV Simulator"},{"key":"ref3","author":"polvara","year":"2017","journal-title":"Autonomous Quadrotor Landing using Deep Reinforcement Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2018.8468611"},{"key":"ref29","author":"gudimella","year":"2017","journal-title":"Deep reinforcement learning for dexterous manipulation with concept networks"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2010.5611206"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICISCE.2016.42"},{"key":"ref7","author":"pham","year":"2018","journal-title":"Autonomous UAV navigation using reinforcement learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref1","author":"zulu","year":"2016","journal-title":"A review of control algorithms for autonomous quadrotors"},{"key":"ref20","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2013.6564793"},{"key":"ref21","author":"omidshafiei","year":"2013","journal-title":"Reinforcement learning-based quadcopter control"},{"key":"ref24","year":"0","journal-title":"OpenAI Gym toolkit"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386021"},{"key":"ref26","year":"0","journal-title":"Gazebo simulator"},{"key":"ref25","year":"0","journal-title":"Robot Operating System"}],"event":{"name":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","location":"Paris, France","start":{"date-parts":[[2019,4,23]]},"end":{"date-parts":[[2019,4,26]]}},"container-title":["2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8806019\/8820291\/08820368.pdf?arnumber=8820368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:20:38Z","timestamp":1658262038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8820368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/codit.2019.8820368","relation":{},"subject":[],"published":{"date-parts":[[2019,4]]}}}