{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:55:46Z","timestamp":1764402946506,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/inista.2019.8778209","type":"proceedings-article","created":{"date-parts":[[2019,7,29]],"date-time":"2019-07-29T20:22:21Z","timestamp":1564431741000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["An Implementation of Vision Based Deep Reinforcement Learning for Humanoid Robot Locomotion"],"prefix":"10.1109","author":[{"given":"Recen","family":"Ozaln","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cagri","family":"Kaymak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ozal","family":"Yildirum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayscgul","family":"Ucar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yakup","family":"Demir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cuneyt","family":"Guzelis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5772\/5618"},{"journal-title":"Emergence of locomotion behaviours in rich environments","year":"2018","author":"heess","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8442201"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2851148"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246907"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3099564.3099567"},{"journal-title":"Bipedal Walking Robot using Deep Deterministic Policy Gradient","year":"0","author":"kumar","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref35","first-page":"1","article-title":"Moving towards in object recognition with deep learning for autonomous driving applications","author":"u\u00e7ar","year":"2016","journal-title":"2016 International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463209"},{"journal-title":"Modelling and dynamic stabilisation of a compliant humanoid robot CoMan","year":"2012","author":"dallali","key":"ref10"},{"year":"0","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843604000083"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1515\/amcs-2016-0046"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MELCON.2014.6820512"},{"key":"ref14","article-title":"Neural locomotion controller design and implementation for humanoid robot HOAP-l","author":"shan","year":"2002","journal-title":"20th Annu Conf Robot Soc Japan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2014.05.008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref17","article-title":"Reinforcement learning for humanoid robot control","author":"danel","year":"2017","journal-title":"poster"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2018.8581309"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925881"},{"key":"ref28","article-title":"Monte-Carlo Planning for Agile Legged Locomotion","author":"clary","year":"2018","journal-title":"Twenty-Eighth International Conference on Automated Planning and Scheduling"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593702"},{"key":"ref27","first-page":"201","author":"xie","year":"0","journal-title":"Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie"},{"key":"ref3","article-title":"Towards monocular vision based obstacle avoidance through deep reinforcement learning","author":"xie","year":"2017","journal-title":"RSS 2017 Workshop New Frontier for Deep Learning in Robotics"},{"key":"ref6","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17 1","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461039"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IDAP.2018.8620916"},{"journal-title":"Towards vision-based deep reinforcement learning for robotic motion control","year":"2015","author":"zhang","key":"ref7"},{"journal-title":"Robots The 500-year Quest to Make Machines Human","year":"2017","author":"russell","key":"ref2"},{"journal-title":"Vision-Based Locomotion for Humanoid Robots","year":"2013","author":"garcia vazquez","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-74666-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref22"},{"key":"ref21","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"journal-title":"Dueling network architectures for deep reinforcement learning","year":"2015","author":"wang","key":"ref26"},{"key":"ref25","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"Proc of the Thirtieth AAAI Conference on Artificial Intelligence"}],"event":{"name":"2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)","start":{"date-parts":[[2019,7,3]]},"location":"Sofia, Bulgaria","end":{"date-parts":[[2019,7,5]]}},"container-title":["2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8771303\/8778201\/08778209.pdf?arnumber=8778209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T17:47:15Z","timestamp":1658080035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8778209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/inista.2019.8778209","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}