{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T07:13:47Z","timestamp":1777187627627,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611275","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"14046-14053","source":"Crossref","is-referenced-by-count":2,"title":["Conditionally Combining Robot Skills using Large Language Models"],"prefix":"10.1109","author":[{"given":"K.R.","family":"Zentner","sequence":"first","affiliation":[{"name":"Univ. of Southern California"}]},{"given":"Ryan","family":"Julian","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Brian","family":"Ichter","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Gaurav S.","family":"Sukhatme","sequence":"additional","affiliation":[{"name":"Univ. of Southern California"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Google ai palm 2"},{"key":"ref2","article-title":"Gpt-3.5"},{"key":"ref3","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref4","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref6","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835397"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/37.257890"},{"key":"ref10","first-page":"4105","article-title":"CoMic: Complementary task learning & mimicry for reusable skills","volume-title":"Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research","author":"Hasenclever"},{"key":"ref11","article-title":"Learning an embedding space for transferable robot skills","volume-title":"International Conference on Learning Representations","author":"Hausman"},{"key":"ref12","article-title":"Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning","author":"Julian","year":"2020"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-33950-0_24","article-title":"Scaling simulation-to-real transfer by learning composable robot skills","volume-title":"International Symposium on Experimental Robotics","author":"Julian"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139389"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981126"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196642"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref19","article-title":"Reinforcement learning for robots using neural networks","author":"Lin","year":"1992"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(92)90058-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392474"},{"key":"ref22","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref23","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref24","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2012.6651537"},{"key":"ref26","article-title":"Mcp: Learning composable hierarchical control with multiplicative compositional policies","volume":"32","author":"Peng","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Tool learning with foundation models","author":"Qin","year":"2023"},{"key":"ref28","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139390"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014237"},{"key":"ref32","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref33","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022"},{"key":"ref34","article-title":"Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents","author":"Wang","year":"2023"},{"key":"ref35","article-title":"Chain of thought prompting elicits reasoning in large language models","author":"Wei","year":"2022"},{"key":"ref36","first-page":"11340","article-title":"Data-efficient hindsight off-policy option learning","volume-title":"International Conference on Machine Learning","author":"Wulfmeier"},{"key":"ref37","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume":"33","author":"Yang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Yu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref40","article-title":"Least-to-most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-6263-1_3"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611275.pdf?arnumber=10611275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:07:28Z","timestamp":1723349248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611275","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}