{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:20:25Z","timestamp":1766132425852,"version":"3.48.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247602","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"8012-8018","source":"Crossref","is-referenced-by-count":0,"title":["Learning Manipulation Skills through Robot Chain-of-Thought with Sparse Failure Guidance"],"prefix":"10.1109","author":[{"given":"Kaifeng","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Qi Zhi Institute"}]},{"given":"Zhao-Heng","family":"Yin","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Weirui","family":"Ye","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"article-title":"RoboCLIP: One demonstration is enough to learn robot policies","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS)","author":"Sontakke","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref4","first-page":"24 824","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 (NeurIPS)"},{"article-title":"Compositional foundation models for hierarchical planning","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS)","author":"Ajay","key":"ref5"},{"article-title":"Do as i can, not as i say: Grounding language in robotic affordances","year":"2022","author":"Ahn","key":"ref6"},{"article-title":"Look before you leap: Unveiling the power of gpt-4v in robotic vision-language planning","year":"2023","author":"Hu","key":"ref7"},{"article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","year":"2022","author":"Huang","key":"ref8"},{"key":"ref9","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"article-title":"Imitation learning from observation with automatic discount scheduling","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197326"},{"key":"ref12","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Matas"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.046"},{"article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Nair","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"article-title":"Palm-e: An embodied multimodal language model","year":"2023","author":"Driess","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"article-title":"Vision-language foundation models as effective robot imitators","volume-title":"International Conference on Learning Representations (ICLR)","author":"Li","key":"ref18"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.049"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning (ICML)","author":"Radford"},{"article-title":"Vision-language models are zero-shot reward models for reinforcement learning","year":"2023","author":"Rocamonde","key":"ref22"},{"key":"ref23","first-page":"23 301","article-title":"Liv: Language-image representations and rewards for robotic control","volume-title":"International Conference on Machine Learning (ICML)","author":"Ma"},{"article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","volume-title":"International Conference on Leanring Representations (ICLR)","author":"Ma","key":"ref24"},{"article-title":"Vision-language models as a source of rewards","year":"2023","author":"Baumli","key":"ref25"},{"article-title":"Rl-vlm-f: Reinforcement learning from vision language foundation model feedback","year":"2024","author":"Wang","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref28","first-page":"32","article-title":"Watch and match: Supercharging imitation with regularized optimal transport","volume-title":"Conference on Robot Learning","author":"Haldar"},{"article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","year":"2021","author":"Yarats","key":"ref29"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247602.pdf?arnumber=11247602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:17:37Z","timestamp":1766132257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247602","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}