{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:31:46Z","timestamp":1730302306961,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/urai.2019.8768681","type":"proceedings-article","created":{"date-parts":[[2019,7,26]],"date-time":"2019-07-26T00:16:33Z","timestamp":1564100193000},"page":"118-123","source":"Crossref","is-referenced-by-count":4,"title":["Multi-rotor Robot Learning to Fly in a Bio-inspired Way Using Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Amir Ramezani","family":"Dooraki","sequence":"first","affiliation":[]},{"given":"Deok-Jin","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.artint.2015.02.001","article-title":"Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots","volume":"247","author":"kompella","year":"2017","journal-title":"Artificial Intelligence"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"CoRR abs\/1509 02971"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.3390\/s18103575","article-title":"An end-to-end deep reinforcement learning-based intelligent agent capable of autonomous exploration in unknown environments","volume":"18","author":"ramezani dooraki","year":"2018","journal-title":"SENSORS"},{"key":"ref16","article-title":"(cad)2rl: Real single-image flight without a single real image","author":"sadeghi","year":"2016","journal-title":"CoRR abs\/1611 04201"},{"key":"ref17","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"CoRR abs\/1502 05477"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR abs\/1707 06347"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref4","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"0"},{"journal-title":"Ros org — powering the world's robots","year":"0","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1729881418775849"},{"journal-title":"Experience imitation and reflection confucius’ conjecture and machine learning","year":"2018","author":"dooraki","key":"ref5"},{"article-title":"Autonomous exploration, active learning and human guidance with open-source Poppy humanoid robot platform and Explauto library","year":"2016","author":"forestier","key":"ref8"},{"journal-title":"Bio-Inspired Artificial Intelligence Theories Methods and Technologies","year":"2008","author":"floreano","key":"ref7"},{"journal-title":"Nature vs nurture How do baby birds learn how to fly?","year":"0","key":"ref2"},{"journal-title":"Gazebo simulator","year":"0","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26054-9_23"},{"journal-title":"Introduction to Reinforcement Learning","year":"1998","author":"sutton","key":"ref20"},{"key":"ref21","article-title":"Learning deep control policies for autonomous aerial vehicles with mpc-guided policy search","author":"zhang","year":"2015","journal-title":"CoRR abs\/1509 06791"}],"event":{"name":"2019 16th International Conference on Ubiquitous Robots (UR)","start":{"date-parts":[[2019,6,24]]},"location":"Jeju, Korea (South)","end":{"date-parts":[[2019,6,27]]}},"container-title":["2019 16th International Conference on Ubiquitous Robots (UR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8765202\/8768488\/08768681.pdf?arnumber=8768681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:17:42Z","timestamp":1658261862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8768681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/urai.2019.8768681","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}