{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T09:20:00Z","timestamp":1776849600891,"version":"3.51.2"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"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":[[2026,2,5]]},"DOI":"10.1109\/icara69401.2026.11480318","type":"proceedings-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:47:13Z","timestamp":1776800833000},"page":"482-487","source":"Crossref","is-referenced-by-count":0,"title":["Curriculum-Based Reward Function Optimization Using Deep Deterministic Policy Gradient for Rotary Inverted Pendulum: An Underactuated System"],"prefix":"10.1109","author":[{"given":"Muhammad Talha","family":"Hassan","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shameer","family":"Ashraf","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Haris","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Abdullah","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neelma","family":"Naz","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Furuta pendulum","volume-title":"Wikipedia","year":"2023"},{"key":"ref2","article-title":"Curriculum Reinforcement Learning for Complex Reward Functions","volume-title":"arXiv preprint","author":"Freitag","year":"2025"},{"key":"ref3","article-title":"9.2: P, I, D, PI, PD, and PID Control","author":"Woolf","year":"2023","journal-title":"Chemical Process Dynamics and Controls, LibreTexts"},{"key":"ref4","article-title":"LQR","volume-title":"Underactuated Robotics","author":"Tedrake","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/picc.2018.8384816"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1687814019842712"},{"issue":"2","key":"ref7","first-page":"16","article-title":"Fuzzy controller for rotary inverted pendulum","volume":"23","author":"Le","year":"2018","journal-title":"Robotica & Management"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.788"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-3544387\/v1","article-title":"Deep Deterministic Policy Gradient Algorithm: A Systematic Review","volume-title":"ResearchGate","author":"Sumiea","year":"2023"},{"issue":"1","key":"ref10","doi-asserted-by":"crossref","first-page":"305","DOI":"10.32604\/cmes.2024.047899","article-title":"Reduced-order observer-based LQR controller design for rotary inverted pendulum","volume":"140","author":"Gao","year":"2024","journal-title":"CMES - Computer Modeling in Engineering and Sciences"},{"key":"ref11","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv preprint","author":"Lillicrap","year":"2019"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v39i15.33679","article-title":"Bootstrapped Reward Shaping","volume-title":"arXiv preprint","author":"Adamczyk","year":"2025"},{"key":"ref13","article-title":"MuJoCo Documentation","volume-title":"MuJoCo Physics Engine"},{"key":"ref14","article-title":"Ziegler-Nichols method","volume-title":"Wikipedia, the free encyclopedia"}],"event":{"name":"2026 12th International Conference on Automation, Robotics and Applications (ICARA)","location":"Istanbul, Turkiye","start":{"date-parts":[[2026,2,5]]},"end":{"date-parts":[[2026,2,7]]}},"container-title":["2026 12th International Conference on Automation, Robotics and Applications (ICARA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11480269\/11480271\/11480318.pdf?arnumber=11480318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T08:20:31Z","timestamp":1776846031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11480318\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icara69401.2026.11480318","relation":{},"subject":[],"published":{"date-parts":[[2026,2,5]]}}}