{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:31:47Z","timestamp":1777735907214,"version":"3.51.4"},"reference-count":46,"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\/icra57147.2024.10611483","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"7493-7500","source":"Crossref","is-referenced-by-count":9,"title":["Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"Eleftherios","family":"Triantafyllidis","sequence":"first","affiliation":[{"name":"The University of Edinburgh,School of Informatics,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Filippos","family":"Christianos","sequence":"additional","affiliation":[{"name":"The University of Edinburgh,School of Informatics,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[{"name":"University College London,Department of Computer Science,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Wish you were here: Hindsight goal selection for long-horizon dexterous manipulation","volume-title":"International Conference on Learning Representations","author":"Davchev"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2019.8843293"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00709-2"},{"key":"ref4","first-page":"1146","article-title":"Decoupled reinforcement learning to stabilise intrinsically-motivated exploration","volume-title":"Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems","author":"Sch\u00e4fer"},{"key":"ref5","article-title":"Learning from delayed rewards","volume-title":"Ph.D. dissertation","author":"Watkins","year":"1989"},{"key":"ref6","article-title":"Continuous control with deep reinforcement learning","volume-title":"4th International Conference on Learning Representations, ICLR 2016","author":"Lillicrap","year":"2016"},{"key":"ref7","first-page":"2778","article-title":"Curiosity-driven exploration by self-supervised prediction","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Pathak"},{"key":"ref8","article-title":"Guiding pretraining in reinforcement learning with large language models","author":"Du","year":"2023"},{"key":"ref9","article-title":"Concrete problems in ai safety","author":"Amodei","year":"2016"},{"key":"ref10","article-title":"Adversarially guided actor-critic","volume-title":"International Conference on Learning Representations","author":"Flet-Berliac"},{"key":"ref11","article-title":"Exploration by random network distillation","volume-title":"International Conference on Learning Representations","author":"Burda"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref13","article-title":"Intrinsically motivated reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"17","author":"Chentanez","year":"2004"},{"key":"ref14","article-title":"On bonus based exploration methods in the arcade learning environment","volume-title":"International Conference on Learning Representations","author":"Taiga"},{"key":"ref15","article-title":"Language to rewards for robotic skill synthesis","author":"Yu","year":"2023"},{"issue":"8","key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref17","article-title":"Reward design with language models","author":"Kwon","year":"2023"},{"key":"ref18","article-title":"Read and reap the rewards: Learning to play atari with the help of instruction manuals","author":"Wu","year":"2023"},{"key":"ref19","article-title":"Grounding large language models in interactive environments with online reinforcement learning","author":"Carta","year":"2023"},{"key":"ref20","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref21","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown","year":"2020"},{"key":"ref22","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00488-2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-020-00395-8"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref29","first-page":"1861","article-title":"Soft actorcritic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Haarnoja"},{"key":"ref30","first-page":"3849","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Gu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3170427.3186500"},{"key":"ref32","article-title":"Goal-conditioned imitation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Ding","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00444-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb2174"},{"key":"ref35","article-title":"Unifying count-based exploration and intrinsic motivation","author":"Bellemare","year":"2016"},{"key":"ref36","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Ostrovski"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2021.3090070"},{"key":"ref38","article-title":"Unity: A general platform for intelligent agents","author":"Juliani","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"issue":"6446","key":"ref40","article-title":"Trends and challenges in robot manipulation","volume-title":"Science","volume":"364","author":"Billard","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref42","article-title":"Generative adversarial imitation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Ho","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3112"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611483"},{"key":"ref45","article-title":"Behaviour suite for reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Osband"},{"key":"ref46","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"}],"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\/10611483.pdf?arnumber=10611483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:18:21Z","timestamp":1723349901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611483","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}