{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:10:20Z","timestamp":1736971820437,"version":"3.33.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801742","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"5813-5820","source":"Crossref","is-referenced-by-count":0,"title":["Robot Generating Data for Learning Generalizable Visual Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Yunfei","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Ying","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Jingzhi","family":"Cui","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Haoran","family":"Huan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Wei","family":"Fu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Jiaxuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Zekai","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}]},{"given":"Yi","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Photorealistic text-to-image diffusion models with deep language understanding","year":"2022","author":"Saharia","key":"ref2"},{"key":"ref3","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Kenton"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref5","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"article-title":"On the opportunities and risks of foundation models","year":"2021","author":"Bommasani","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref8","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning.","author":"Fujimoto","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.019"},{"article-title":"Awac: Accelerating online reinforcement learning with offline datasets","year":"2020","author":"Nair","key":"ref10"},{"key":"ref11","first-page":"1518","article-title":"Actionable models: Unsupervised offline reinforcement learning of robotic skills","volume-title":"International Conference on Machine Learning","author":"Chebotar"},{"key":"ref12","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning.","author":"Jang","year":"2022"},{"article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","year":"2021","author":"Kalashnikov","key":"ref13"},{"key":"ref14","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Conference on robot learning","author":"Lynch"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"article-title":"Learning universal policies via textguided video generation","year":"2023","author":"Dai","key":"ref16"},{"key":"ref17","first-page":"1179","article-title":"Conservative qlearning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"1702","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble","volume-title":"Conference on Robot Learning","author":"Lee"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981999"},{"article-title":"Generalization with lossy affordances: Leveraging broad offline data for learning visuomotor tasks","volume-title":"6th Annual Conference on Robot Learning","author":"Fang","key":"ref22"},{"article-title":"Hiql: Offline goal-conditioned rl with latent states as actions","year":"2023","author":"Park","key":"ref23"},{"article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"6th Annual Conference on Robot Learning","author":"Brohan","key":"ref24"},{"key":"ref25","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Conference on Robot Learning.","author":"Huang","year":"2023"},{"article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","year":"2022","author":"Zeng","key":"ref26"},{"key":"ref27","first-page":"302","article-title":"Bootstrap your own skills: Learning to solve new tasks with large language model guidance","volume-title":"Conference on Robot Learning.","author":"Zhang","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref29","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","volume-title":"Conference on robot learning.","author":"Florensa","year":"2017"},{"key":"ref30","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","volume-title":"International conference on machine learning.","author":"Florensa","year":"2018"},{"key":"ref31","article-title":"Exploration via hindsight goal generation","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"Automated curriculum generation through setter-solver interactions","author":"Racaniere","year":"2019","journal-title":"International conference on learning representations"},{"article-title":"Paired openended trailblazer (poet): Endlessly generating increasingly complex and diverse learning environments and their solutions","year":"2019","author":"Wang","key":"ref33"},{"key":"ref34","first-page":"9940","article-title":"Enhanced poet: Open-ended reinforcement learning through unbounded invention of learning challenges and their solutions","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref35","first-page":"13049","article-title":"Emergent complexity and zero-shot transfer via unsupervised environment design","volume":"33","author":"Dennis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref36","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"International conference on machine learning.","author":"Cobbe","year":"2020"},{"key":"ref37","first-page":"66","article-title":"Learning by cheating","volume-title":"Conference on Robot Learning.","author":"Chen","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abg5810"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref41","article-title":"A system for general in-hand object re-orientation","author":"Chen","year":"2021","journal-title":"Conference on Robot Learning"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","volume-title":"CoRR","author":"Schulman","year":"2017"},{"key":"ref43","first-page":"1312","article-title":"Universal value function approximators","volume-title":"International conference on machine learning.","author":"Schaul","year":"2015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636280"},{"key":"ref45","first-page":"11525","article-title":"Objectcentric learning with slot attention","volume":"33","author":"Locatello","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"D4rl: Datasets for deep data-driven reinforcement learning","year":"2020","author":"Fu","key":"ref49"},{"key":"ref50","first-page":"892","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"Conference on Robot Learning.","author":"Nair","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801742.pdf?arnumber=10801742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:30:29Z","timestamp":1736969429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801742\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801742","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}