{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:47:31Z","timestamp":1766062051810,"version":"3.48.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3638051","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:59:03Z","timestamp":1764269943000},"page":"208397-208413","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time HIL Implementation of DDPG-Based Reinforcement Learning Controller for a DC Servo Motor With Inertia Disc and Rotary Inverted Pendulum"],"prefix":"10.1109","volume":"13","author":[{"given":"K.","family":"Vijaya Lakshmi","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6260-9397","authenticated-orcid":false,"given":"M.","family":"Manimozhi","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"123","article-title":"Challenges in nonlinear control systems","volume":"45","author":"Smith","year":"2020","journal-title":"J. Control Eng."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1115\/1.3426465"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref3"},{"volume-title":"QUBE-Servo 2 System","year":"2021","key":"ref4"},{"key":"ref5","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref7","article-title":"Humanoid robotics and pendulum balancing","volume":"124","author":"Bergerman","year":"2020","journal-title":"Robot. Auton. Syst."},{"issue":"1","key":"ref8","first-page":"123","article-title":"Satellite attitude control for emergency mode using reaction wheels and magnetic torques","volume":"61","author":"Lee","year":"2025","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3457538"},{"issue":"2","key":"ref10","first-page":"109","article-title":"Performance evaluation of cascade PID controllers in RIP systems","volume":"55","author":"Govind","year":"2020","journal-title":"J. Control Syst. Appl."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3415494"},{"issue":"1","key":"ref12","first-page":"45","article-title":"Hybrid LQR-SMC for robust control of rotary inverted pendulum","volume":"63","author":"Chawla","year":"2021","journal-title":"J. Eng. Control"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2022.100632"},{"issue":"2","key":"ref14","first-page":"102","article-title":"Fuzzy PID control of rotary inverted pendulum","volume":"40","author":"Ullah","year":"2023","journal-title":"J. Appl. Control Eng."},{"key":"ref15","first-page":"55","article-title":"Model-based control of rotary inverted pendulum using DSPs","volume-title":"Proc. Int. Conf. Control Autom.","author":"Pan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/act9040095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.22190\/FUME231011044Z"},{"volume-title":"Deep Reinforcement Learning Hands-on: A Practical and Easy-to-Follow Guide to RL From Q-Learning and DQNs to PPO and RLHF","year":"2024","author":"Lapan","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s44196-023-00389-1"},{"key":"ref20","first-page":"123456","article-title":"A deep reinforcement learning-based framework for continuous control in smart industrial systems","volume":"10","author":"Alshahrani","year":"2022","journal-title":"IEEE Access"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.9790\/0661-2605032628"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e30697"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3074535"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06764-9"},{"volume-title":"QUBE-Servo 2: Rotary Inverted Pendulum & Inertial Disc System","year":"2020","key":"ref25"},{"volume-title":"DC Motor Modeling and Control\u2014QUBE-Servo 2 Instructor\u2019s Guide","year":"2018","key":"ref26"},{"volume-title":"Rotary Inverted Pendulum: Instructor Manual and Modelling Notes","year":"2020","key":"ref27"},{"key":"ref28","first-page":"350","volume-title":"Reinforcement Learning","author":"Kauffman","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1201\/9781439821091"},{"article-title":"Mastering reinforcement learning: Foundations, algorithms, and real-world applications","year":"2024","author":"Song","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cisce52179.2021.9445914"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s40815-022-01293-0"},{"key":"ref33","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Duan"},{"volume-title":"Rotary Inverted Pendulum Experiment\u2014Instructor\u2019s Guide","year":"2020","key":"ref34"},{"issue":"2","key":"ref35","first-page":"1712","article-title":"Artificial bee colony based PD controller design for Quanser QUBE servo","volume":"12","author":"Lakshmi","year":"2020","journal-title":"J. Adv. Res. Dyn. Control Syst."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-020-05161-7"},{"key":"ref37","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Fujimoto"},{"key":"ref38","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. (ICML)","author":"Haarnoja"},{"volume-title":"Train Reinforcement Learning Agents to Control Quanser QUBE Pendulum","year":"2025","key":"ref39"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11270871.pdf?arnumber=11270871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:43:00Z","timestamp":1766061780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11270871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3638051","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}