{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T01:46:59Z","timestamp":1743644819025,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T00:00:00Z","timestamp":1673913600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T00:00:00Z","timestamp":1673913600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003052","name":"MOTIE (Ministry of Trade, Industry, and Energy) in Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003661","name":"Korea Institute for Advancement of Technology (KIAT)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,17]]},"DOI":"10.1109\/sii55687.2023.10039306","type":"proceedings-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T21:26:35Z","timestamp":1676582795000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["DDPG Reinforcement Learning Experiment for Improving the Stability of Bipedal Walking of Humanoid Robots"],"prefix":"10.1109","author":[{"given":"Yeonghun","family":"Chun","sequence":"first","affiliation":[{"name":"Hanyang University,Department of Convergence Robot System,Ansan,Republic of Korea,15588"}]},{"given":"Junghun","family":"Choi","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Mechatronics Engineering,Ansan,Republic of Korea,15588"}]},{"given":"Injoon","family":"Min","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Convergence Robot System,Ansan,Republic of Korea,15588"}]},{"given":"Minsung","family":"Ahn","sequence":"additional","affiliation":[{"name":"University of California,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA,90095"}]},{"given":"Jeakweon","family":"Han","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Robotics,Ansan,Republic of Korea,15588"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-2993-7_2"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref5","first-page":"1","article-title":"Data efficient reinforcement learning for legged robots","volume-title":"Conference on Robot Learning, May 2020","author":"Yang","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS48895.2020.9073987"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065709002002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2005.1573573"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094427"},{"key":"ref10","article-title":"Bipedal walking robot using deep deterministic policy gradient","author":"Kumar","year":"2018","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593722"},{"key":"ref12","article-title":"Iterative reinforcement learning based design of dynamic locomotion skills for cassie","author":"Xie","year":"2019","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561814"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app9030502"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561717"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650765"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids.2011.6100850"},{"key":"ref19","article-title":"Towards Real Robot Learning in the Wild: A Case Study in Bipedal Locomotion","volume-title":"Conference on Robot Learning","author":"Bloesch","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.053"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1241826"},{"issue":"3\u20134","key":"ref22","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref23","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"1008","article-title":"Actor-critic algorithms","author":"Konda","year":"2000","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 IEEE\/SICE International Symposium on System Integration (SII)","start":{"date-parts":[[2023,1,17]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2023,1,20]]}},"container-title":["2023 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10038976\/10039084\/10039306.pdf?arnumber=10039306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T14:16:43Z","timestamp":1707833803000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10039306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,17]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/sii55687.2023.10039306","relation":{},"subject":[],"published":{"date-parts":[[2023,1,17]]}}}