{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:07:44Z","timestamp":1782317264438,"version":"3.54.5"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2023.3344393","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T19:49:47Z","timestamp":1702928987000},"page":"7490-7499","source":"Crossref","is-referenced-by-count":17,"title":["Comparative Analysis of Reinforcement Learning Algorithms for Bipedal Robot Locomotion"],"prefix":"10.1109","volume":"12","author":[{"given":"Omur","family":"Aydogmus","sequence":"first","affiliation":[{"name":"Department of Mechatronics Engineering, Faculty of Technology, Fırat University, Elazig, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2306-6008","authenticated-orcid":false,"given":"Musa","family":"Yilmaz","sequence":"additional","affiliation":[{"name":"Center for Environmental Research and Technology, Bourns College of Engineering, University of California at Riverside, Riverside, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.17694\/bajece.983350"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15226-9_11"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-021-00059-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3324580"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-018-0184-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4488-0_58"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2020.1837670"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s42242-019-00038-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1487\/1\/012048"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/s22124440"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061381"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2019.04.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3139909"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3327705"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3317918"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3308050"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.1054239"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3151771"},{"key":"ref21","article-title":"Teaching a robot to walk using reinforcement learning","author":"Dibachi","year":"2021","journal-title":"arXiv:2112.07031"},{"key":"ref22","article-title":"Evolutionary selective imitation: Interpretable agents by imitation learning without a demonstrator","author":"Eliya","year":"2020","journal-title":"arXiv:2009.08403"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.47495\/okufbed.1031976"},{"key":"ref24","article-title":"Soft actor-critic with inhibitory networks for faster retraining","author":"Ide","year":"2022","journal-title":"arXiv:2202.02918"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref26","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref28","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3125895"},{"key":"ref31","article-title":"Algorithms for hyper-parameter optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Bergstra"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/rs13224694"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10364844.pdf?arnumber=10364844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:49:02Z","timestamp":1705690142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10364844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3344393","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}