{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T04:18:26Z","timestamp":1793679506408,"version":"4.5.1"},"reference-count":44,"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\/icra57147.2024.10611331","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T13:51:05Z","timestamp":1723125065000},"page":"3153-3160","source":"Crossref","is-referenced-by-count":31,"title":["Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Annie","family":"Xie","sequence":"first","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Lee","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ted","family":"Xiao","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"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":"19884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"Laskin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","author":"Yarats","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref4","first-page":"1992","article-title":"Visual imitation made easy","volume-title":"Conference on Robot Learning","author":"Young"},{"key":"ref5","article-title":"Learning dense visual descriptors using image augmentations for robot manipulation tasks","author":"Graf","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197331"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref9","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref10","article-title":"Rrl: Resnet as representation for reinforcement learning","author":"Shah","year":"2021"},{"key":"ref11","article-title":"The unsurprising effectiveness of pre-trained vision models for control","author":"Parisi","year":"2022"},{"key":"ref12","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref13","first-page":"906","article-title":"Multiple interactions made easy (mime): Large scale demonstrations data for imitation","volume-title":"Conference on robot learning","author":"Sharma"},{"key":"ref14","first-page":"879","article-title":"Roboturk: A crowdsourcing platform for robotic skill learning through imitation","volume-title":"Conference on Robot Learning","author":"Mandlekar"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968114"},{"key":"ref16","article-title":"Robonet: Large-scale multi-robot learning","author":"Dasari","year":"2019"},{"key":"ref17","article-title":"Bridge data: Boosting generalization of robotic skills with cross-domain datasets","author":"Ebert","year":"2021"},{"key":"ref18","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref20","first-page":"23885","article-title":"Partial success in closing the gap between human and machine vision","volume":"34","author":"Geirhos","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on Robot Learning","author":"Kalashnikov"},{"key":"ref22","article-title":"Rt-1: Robotics transformer for real-world control at scale","author":"Brohan","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref26","first-page":"12627","article-title":"Sim-to-real via simto-sim: Data-efficient robotic grasping via randomized-to-canonical adaptation networks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"James"},{"key":"ref27","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on robot learning","author":"Yu"},{"key":"ref28","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"International conference on machine learning","author":"Cobbe"},{"key":"ref29","article-title":"The distracting control suite\u2013a challenging benchmark for reinforcement learning from pixels","author":"Stone","year":"2021"},{"key":"ref30","article-title":"Kitchenshift: Evaluating zero-shot generalization of imitation-based policy learning under domain shifts","volume-title":"NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications","author":"Xing"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref33","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref34","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref35","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020"},{"key":"ref36","first-page":"3680","article-title":"Stabilizing deep q-learning with convnets and vision transformers under data augmentation","volume":"34","author":"Hansen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning","author":"Julian","year":"2020"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA48891.2023.10160594","article-title":"Train offline, test online: A real robot learning benchmark","volume-title":"Deep Reinforcement Learning Workshop NeurIPS","author":"Zhou"},{"key":"ref39","article-title":"Scanned Objects MuJoCo Models","author":"Zakka","year":"2022"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA46639.2022.9811809","article-title":"Google scanned objects: A high-quality dataset of 3d scanned household items","author":"Downs","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","article-title":"Rt-2: Visionlanguage-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"}],"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\/10611331.pdf?arnumber=10611331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T00:12:20Z","timestamp":1723335140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611331","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}