{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:36:00Z","timestamp":1774629360397,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6240020443,62073225,62203134"],"award-info":[{"award-number":["6240020443,62073225,62203134"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127726","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"8242-8248","source":"Crossref","is-referenced-by-count":1,"title":["Automated Hybrid Reward Scheduling Via Large Language Models for Robotic Skill Learning"],"prefix":"10.1109","author":[{"given":"Changxin","family":"Huang","sequence":"first","affiliation":[{"name":"Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China,518061"}]},{"given":"Junyang","family":"Liang","sequence":"additional","affiliation":[{"name":"Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China,518061"}]},{"given":"Yanbin","family":"Chang","sequence":"additional","affiliation":[{"name":"Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China,518061"}]},{"given":"Jingzhao","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China,518061"}]},{"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China,518061"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref2","first-page":"1312","article-title":"Universal value function approximators","volume-title":"International conference on machine learning","author":"Schaul","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref5","first-page":"1060","article-title":"Discovering reinforcement learning algorithms","volume":"33","author":"Oh","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610747"},{"key":"ref8","article-title":"H-index: Visual reinforcement learning with hand-informed representations for dexterous manipulation","volume":"36","author":"Ze","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160275"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339515"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561491"},{"key":"ref12","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Hybrid reward architecture for reinforcement learning","volume":"30","author":"Van Seijen","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223407"},{"key":"ref16","article-title":"Eureka: Humanlevel reward design via coding large language models","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"761","article-title":"Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction","volume-title":"The 10th International Conference on Autonomous Agents and Multiagent Systems","volume":"2","author":"Sutton","year":"2011"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-024-00550-5"},{"key":"ref20","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"79081","article-title":"Leveraging pre-trained large language models to construct and utilize world models for model-based task planning","volume":"36","author":"Guan","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref26","article-title":"Language to rewards for robotic skill synthesis","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Robogen: Towards unleashing infinite data for automated robot learning via generative simulation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3410155"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610855"},{"key":"ref31","article-title":"Llm+ p: Empowering large language models with optimal planning proficiency","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610981"},{"key":"ref33","article-title":"Highdimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Explainable reinforcement learning via reward decomposition","volume-title":"IJCAI\/ECAI Workshop on explainable artificial intelligence","author":"Juozapaitis","year":"2019"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127726.pdf?arnumber=11127726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:04:08Z","timestamp":1756879448000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127726","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}