{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:39:00Z","timestamp":1770917940407,"version":"3.50.1"},"reference-count":55,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128783","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"4470-4477","source":"Crossref","is-referenced-by-count":2,"title":["CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills Using Large Language Models"],"prefix":"10.1109","author":[{"given":"Kanghyun","family":"Ryu","sequence":"first","affiliation":[{"name":"University of California,Mechanical Engineering,Berkeley"}]},{"given":"Qiayuan","family":"Liao","sequence":"additional","affiliation":[{"name":"University of California,Mechanical Engineering,Berkeley"}]},{"given":"Zhongyu","family":"Li","sequence":"additional","affiliation":[{"name":"University of California,Mechanical Engineering,Berkeley"}]},{"given":"Payam","family":"Delgosha","sequence":"additional","affiliation":[{"name":"University of Illinois, Urbana-Champaign,Computer Science department"}]},{"given":"Koushil","family":"Sreenath","sequence":"additional","affiliation":[{"name":"University of California,Mechanical Engineering,Berkeley"}]},{"given":"Negar","family":"Mehr","sequence":"additional","affiliation":[{"name":"University of California,Mechanical Engineering,Berkeley"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299188"},{"issue":"181","key":"ref6","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241285161"},{"key":"ref8","article-title":"Learning agile motor skills on quadrupedal robots using curriculum learning","volume":"3","author":"Tang","year":"2021","journal-title":"International Con-ference on Robot Intelligence Technology and Applications"},{"key":"ref9","article-title":"Guided curriculum learning for walking over complex terrain","volume-title":"Australasian Conference on Robotics and Automation 2020","author":"Tidd"},{"key":"ref10","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref12","first-page":"482","article-title":"Re-verse curriculum generation for reinforcement learning","volume-title":"Conference on robot learning","author":"Florensa"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794206"},{"issue":"152","key":"ref14","first-page":"1","article-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning","volume":"23","author":"Forestier","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3251193"},{"key":"ref16","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","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":"ref20","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on robot learning","author":"Brohan"},{"key":"ref21","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Gensim: Generating robotic simulation tasks via large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref25","article-title":"Robogen: Towards unleashing infinite data for automated robot learning via generative simulation","volume-title":"Forty-first International Conference on Machine Learning","author":"Wang"},{"key":"ref26","article-title":"Environment curriculum generation via large language models","volume-title":"8th Annual Conference on Robot Learning","author":"Liang"},{"key":"ref27","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ma"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01554"},{"key":"ref29","article-title":"Berkeley humanoid: A research platform for learning-based control","volume-title":"arXiv preprint","author":"Liao","year":"2024"},{"key":"ref30","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/671"},{"key":"ref32","article-title":"Unsupervised curricula for visual meta-reinforcement learning","volume":"32","author":"Jabri","year":"2019","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"ref34","first-page":"1489","article-title":"Adaptive teaching in heterogeneous agents: Balancing surprise in sparse reward scenarios","volume-title":"Proceedings of the 6th Annual Learning for Dynamics & Control Conference, vol. 242 of Proceedings of Machine Learning Research","author":"Clark"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref36","article-title":"It takes four to tango: Multiagent self play for automatic curriculum generation","author":"Du","year":"2022","journal-title":"International Con-ference on Learning Representations"},{"key":"ref37","first-page":"78824","article-title":"Cqm: Curriculum reinforcement learning with a quantized world model","volume":"36","author":"Lee","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.094"},{"key":"ref39","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International conference on machine learning","author":"Huang"},{"key":"ref40","article-title":"Long-horizon locomotion and manipulation on a quadrupedal robot with large language models","author":"Ouyang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Value function spaces: Skill-centric state abstractions for long-horizon reasoning","volume-title":"International Conference on Learning Representations","author":"Shah"},{"key":"ref42","first-page":"29529","article-title":"Ella: Exploration through learned language abstraction","volume":"34","author":"Mirchandani","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/331"},{"key":"ref44","first-page":"374","article-title":"Language to rewards for robotic skill synthesis","volume-title":"Conference on Robot Learning","author":"Yu"},{"key":"ref45","article-title":"Reward design with language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kwon"},{"key":"ref46","article-title":"Vision-language models are zero-shot reward models for reinforcement learning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Rocamonde"},{"key":"ref47","article-title":"Self-refined large language model as automated reward function designer for deep reinforcement learning in robotics","author":"Song","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.125"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cdc56724.2024.10885862"},{"key":"ref50","author":"de Lazcano","year":"2023","journal-title":"Gymnasium robotics"},{"issue":"268","key":"ref51","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref52","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref53","article-title":"Hind-sight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref55","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"}],"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\/11128783.pdf?arnumber=11128783","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:08:56Z","timestamp":1756879736000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128783\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128783","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}