{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T03:54:06Z","timestamp":1782791646542,"version":"3.54.5"},"reference-count":29,"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\/icra55743.2025.11127622","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"9011-9017","source":"Crossref","is-referenced-by-count":7,"title":["ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models"],"prefix":"10.1109","author":[{"given":"Runyu","family":"Ma","sequence":"first","affiliation":[{"name":"Cognitive Robotics, Delft University of Technology,The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jelle","family":"Luijkx","sequence":"additional","affiliation":[{"name":"Cognitive Robotics, Delft University of Technology,The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zlatan","family":"Ajanovi\u0107","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jens","family":"Kober","sequence":"additional","affiliation":[{"name":"Cognitive Robotics, Delft University of Technology,The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Towards a unified agent with foundation models","volume-title":"in Workshop on Reincarnating Reinforcement Learning at ICLR","author":"Di Palo","year":"2023"},{"key":"ref2","year":"2023","journal-title":"GPT-4 technical report"},{"key":"ref3","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning (ICML)","author":"Huang","year":"2022"},{"key":"ref4","article-title":"Socratic models: Composing zeroshot multimodal reasoning with language","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zeng","year":"2023"},{"key":"ref5","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Conference on Robot Learning (CoRL)","author":"Huang","year":"2023"},{"key":"ref6","article-title":"Grounding large language models in interactive environments with online reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Carta","year":"2023"},{"key":"ref7","article-title":"Position: LLMs can\u2019t plan, but can help planning in LLM-modulo frameworks","volume-title":"International Conference on Machine Learning (ICML)","author":"Kambhampati","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref10","article-title":"Large language models are zero-shot reasoners","author":"Kojima","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref11","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning (CoRL)","author":"Brohan","year":"2023"},{"key":"ref12","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Conference on Robot Learning (CoRL)","author":"Huang","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref15","article-title":"Reward design with language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kwon","year":"2023"},{"key":"ref16","article-title":"Language to rewards for robotic skill synthesis","volume-title":"Conference on Robot Learning (CoRL)","author":"Yu","year":"2023"},{"key":"ref17","author":"Song","year":"2023","journal-title":"Self-refined large language model as automated reward function designer for deep reinforcement learning in robotics"},{"key":"ref18","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ma","year":"2024"},{"key":"ref19","article-title":"Guiding pretraining in reinforcement learning with large language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Du","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611483"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3400189"},{"key":"ref22","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Zeng","year":"2021"},{"key":"ref23","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning (ICML)","author":"Haarnoja","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"issue":"1","key":"ref25","first-page":"12348","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"The Journal of Machine Learning Research"},{"key":"ref26","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Gu","year":"2022"},{"key":"ref27","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Shridhar","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2024.3433172"},{"key":"ref29","volume-title":"The Delft AI Cluster (DAIC), RRID:SCR_025091","year":"2024"}],"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\/11127622.pdf?arnumber=11127622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:05:20Z","timestamp":1756879520000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127622","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}