{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T08:03:42Z","timestamp":1777622622564,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tcds.2025.3551298","type":"journal-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T13:47:00Z","timestamp":1741873620000},"page":"1141-1152","source":"Crossref","is-referenced-by-count":1,"title":["AutoSkill: Hierarchical Open-Ended Skill Acquisition for Long-Horizon Manipulation Tasks via Language-Modulated Rewards"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1361-4824","authenticated-orcid":false,"given":"Zhenyang","family":"Lin","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0022-7219","authenticated-orcid":false,"given":"Yurou","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2148-1846","authenticated-orcid":false,"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"30","key":"ref1","first-page":"1","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3240936"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3190850"},{"key":"ref5","first-page":"287","article-title":"Do as I can, not as I say: Grounding Language in Robotic Affordances","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Ichter","year":"2023"},{"key":"ref6","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Huang","year":"2022"},{"key":"ref7","first-page":"23","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Rana","year":"2023"},{"issue":"39","key":"ref8","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","first-page":"729","article-title":"Demonstration-guided reinforcement learning with learned skills","volume-title":"Proc. 5th Conf. Robot Learn.","volume":"164","author":"Pertsch","year":"2022"},{"key":"ref10","article-title":"Parrot: Data-driven behavioral priors for reinforcement learning","volume-title":"Int. Conf. Learn. Represent.","author":"Singh","year":"2021"},{"key":"ref11","first-page":"38600","article-title":"Aspire: Adaptive skill priors for reinforcement learning","volume-title":"Proc. Adv. Neur. Inf. Process. Syst.","volume":"35","author":"Xu","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.074"},{"key":"ref13","first-page":"55681","article-title":"Roboclip: One demonstration is enough to learn robot policies","volume-title":"Advances in Neural Inf. Process. Syst.","volume":"36","author":"Sontakke","year":"2023"},{"key":"ref14","article-title":"Vision-language models are zero-shot reward models for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rocamonde","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3339400"},{"key":"ref16","article-title":"Learning grounded action abstractions from language","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Wong","year":"2024"},{"key":"ref17","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","volume":"100","author":"Gupta","year":"2020"},{"key":"ref18","article-title":"Hierarchical few-shot imitation with skill transition models","volume-title":"Int. Conf. Learn. Represent.","author":"Hakhamaneshi","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068891"},{"key":"ref20","first-page":"188","article-title":"Accelerating reinforcement learning with learned skill priors","volume-title":"Proc. 2020 Conf. Robot Learn.","volume":"155","author":"Pertsch","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3315513"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13754"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635941"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611129"},{"key":"ref25","article-title":"Never-ending embodied robot learning","author":"Liang","year":"2024"},{"key":"ref26","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proc. 5th Conf. Robot Learn.","volume":"164","author":"Jang","year":"2022"},{"key":"ref27","first-page":"892","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Nair","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref29","first-page":"22304","article-title":"Compositional foundation models for hierarchical planning","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Ajay","year":"2023"},{"key":"ref30","article-title":"League++: Empowering continual robot learning through guided skill acquisition with large language models","author":"Li","year":"2024","journal-title":"Proc. ICLR Workshop Large Lang. Model (LLM) Agents"},{"key":"ref31","article-title":"Look before you leap: Unveiling the power of gpt-4v in robotic vision-language planning","author":"Hu","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref33","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Huang","year":"2023"},{"key":"ref34","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref36","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Ma","year":"2024"},{"key":"ref37","article-title":"Text2reward: Reward shaping with language models for reinforcement learning","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Xie","year":"2024"},{"key":"ref38","first-page":"302","article-title":"Bootstrap your own skills: Learning to solve new tasks with large language model guidance","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Zhang","year":"2023"},{"key":"ref39","article-title":"Plan-seq-learn: Language model guided RL for solving long horizon robotics tasks","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Dalal","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10226"},{"key":"ref41","first-page":"1820","article-title":"Mimicgen: A data generation system for scalable robot learning using human demonstrations","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Mandlekar","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1177\/027836499501400103"},{"key":"ref43","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref45","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref46","article-title":"Constrained ensemble exploration for unsupervised skill discovery","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Bai","year":"2024"},{"key":"ref47","article-title":"Vision-language models as a source of rewards","author":"Chan","year":"2023","journal-title":"2nd Agent Learn. Open-Endedness Workshop"},{"key":"ref48","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref49","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref52","article-title":"Adaptive mobile manipulation for articulated objects in the open world","author":"Xiong","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00996"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11197738\/10924760.pdf?arnumber=10924760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T18:33:19Z","timestamp":1765909999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10924760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":53,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2025.3551298","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}