{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T08:23:18Z","timestamp":1787732598147,"version":"build-2784847793"},"reference-count":60,"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\/iros60139.2025.11246854","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"2352-2359","source":"Crossref","is-referenced-by-count":3,"title":["Affordance-Guided Reinforcement Learning via Visual Prompting"],"prefix":"10.1109","author":[{"given":"Olivia Y.","family":"Lee","sequence":"first","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annie","family":"Xie","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuan","family":"Fang","sequence":"additional","affiliation":[{"name":"Cornell University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karl","family":"Pertsch","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chelsea","family":"Finn","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2021"},{"key":"ref3","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.019"},{"key":"ref5","article-title":"Fine-tuning offline policies with optimistic action selection","volume-title":"Deep Reinforcement Learning Workshop NeurIPS 2022","author":"Mark"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610421"},{"key":"ref7","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Learning robust rewards with adverserial inverse reinforcement learnin","volume-title":"International Conference on Learning Representations","author":"Fu"},{"key":"ref9","article-title":"Variational inverse control with events: A general framework for data-driven reward definition","volume":"31","author":"Fu","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","first-page":"40","article-title":"Few-shot goal inference for visuomotor learning and planning","volume-title":"Conference on Robot Learning","author":"Xie"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.073"},{"key":"ref12","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref13","article-title":"Rt-2: Visionlanguage-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref14","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning","author":"Ahn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"ref16","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","author":"Huang","year":"2022"},{"key":"ref17","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Conference on Robot Learning","author":"Huang"},{"key":"ref18","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref20","article-title":"Pivot: Iterative visual prompting elicits actionable knowledge for vlms","author":"Nasiriany","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cdc56724.2024.10885862"},{"key":"ref22","article-title":"Vima: General robot manipulation with multimodal prompts","volume-title":"Fortieth International Conference on Machine Learning","author":"Jiang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160591"},{"key":"ref24","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023"},{"key":"ref25","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"International Conference on Learning Representations","author":"Ma"},{"key":"ref26","article-title":"Language to rewards for robotic skill synthesis","volume-title":"Conference on Robot Learning","author":"Yu"},{"key":"ref27","article-title":"LM-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"6th Annual Conference on Robot Learning","author":"Shah"},{"key":"ref28","first-page":"14743","article-title":"Zero-shot reward specification via grounded natural language","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Mahmoudieh"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02319"},{"key":"ref30","article-title":"On the opportunities and risks of foundation models","author":"B","year":"2022"},{"key":"ref31","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","volume-title":"International Conference on Learning Representations","author":"Zeng"},{"key":"ref32","article-title":"Planning with large language models via corrective re-prompting","volume-title":"Foundation Models for Decision Making Workshop at NeurIPS 2022","author":"Raman"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.30006"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref35","article-title":"Clip-nav: Using clip for zero-shot vision-and-language navigation","author":"Dorbala","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref37","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref38","article-title":"Rt-trajectory: Robotic task generalization via hindsight trajectory sketches","author":"Gu","year":"2023"},{"key":"ref39","article-title":"3dllm: Injecting the 3d world into large language models","author":"Hong","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","article-title":"Chat-3d v2: Bridging 3d scene and large language models with object identifiers","author":"Huang","year":"2023"},{"key":"ref41","article-title":"Chat-3d: Dataefficiently tuning large language model for universal dialogue of 3d scenes","author":"Wang","year":"2023"},{"key":"ref42","article-title":"Gpt-4o system card","year":"2024"},{"key":"ref43","article-title":"Gemini: A family of highly capable multimodal models","author":"Google","year":"2024"},{"key":"ref44","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"Conference on Robot Learning","author":"Nair"},{"key":"ref45","article-title":"Rl-vlm-f: Reinforcement learning from vision language foundation model feedback","volume-title":"Proceedings of the 41th International Conference on Machine Learning","author":"Wang"},{"key":"ref46","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Huang"},{"key":"ref47","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref48","article-title":"Autonomous reinforcement learning: Formalism and benchmarking","volume-title":"International Conference on Learning Representations","author":"Sharma"},{"key":"ref49","article-title":"Autonomous robotic reinforcement learning with asynchronous human feedback","volume-title":"Conference on Robot Learning","author":"Balsells"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref51","first-page":"308","article-title":"Fully autonomous real-world reinforcement learning with applications to mobile manipulation","volume-title":"Proceedings of the 5th Conference on Robot Learning","volume":"164","author":"Sun"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref53","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning","author":"Walke"},{"key":"ref54","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"International Conference on Learning Representations","author":"Zhu"},{"key":"ref55","article-title":"Adaptive mobile manipulation for articulated objects in the open world","author":"Xiong","year":"2024"},{"key":"ref56","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref58","article-title":"Self-improving robots: End-to-end autonomous visuomotor reinforcement learning","volume-title":"7th Annual Conference on Robot Learning","author":"Sharma"},{"key":"ref59","article-title":"Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning","author":"Nakamoto","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.062"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"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\/11246854.pdf?arnumber=11246854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:20:48Z","timestamp":1766132448000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246854","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}