{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T05:45:24Z","timestamp":1744091124255,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"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":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.01337","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:56:41Z","timestamp":1664308601000},"page":"13729-13738","source":"Crossref","is-referenced-by-count":32,"title":["Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation"],"prefix":"10.1109","author":[{"given":"Stephen","family":"James","sequence":"first","affiliation":[{"name":"Dyson Robotics Lab, Imperial College London"}]},{"given":"Kentaro","family":"Wada","sequence":"additional","affiliation":[{"name":"Dyson Robotics Lab, Imperial College London"}]},{"given":"Tristan","family":"Laidlow","sequence":"additional","affiliation":[{"name":"Dyson Robotics Lab, Imperial College London"}]},{"given":"Andrew J.","family":"Davison","sequence":"additional","affiliation":[{"name":"Dyson Robotics Lab, Imperial College London"}]}],"member":"263","reference":[{"key":"ref39","first-page":"14540","article-title":"MoreFusion: Multi-object reasoning for 6D pose estimation from volumetric fusion","author":"sucar","year":"0","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref38","first-page":"5092","article-title":"Probabilistic 3D multilabel real-time mapping for multi-object manipulation","author":"okada","year":"0","journal-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36460-9_27"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/2.30724"},{"key":"ref31","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"journal-title":"Sqil Imitation learning via reinforcement learning with sparse rewards","year":"2019","author":"siddharth","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/MRA.2012.2205651","volume":"19","author":"sucan","year":"2012","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004787"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225029"},{"key":"ref40","first-page":"1789","article-title":"Pixelattentive policy gradient for multi-fingered grasping in cluttered scenes","author":"wu","year":"0","journal-title":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref11","first-page":"1690","article-title":"Humanoid robot localization in complex indoor environments","author":"armin","year":"0","journal-title":"2010 IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"journal-title":"Bingham policy parameterization for 3d rotations in reinforcement learning","year":"2022","author":"james","key":"ref12"},{"key":"ref13","first-page":"783","article-title":"Task-embedded control networks for few-shot imitation learning","author":"bloesch","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140817"},{"key":"ref15","article-title":"3D simulation for robot arm control with deep Q-learning","author":"james","year":"0","journal-title":"Conference on Neural Information Processing Systems Workshop (Deep Learning for Action and Interaction)"},{"key":"ref16","article-title":"Davison. RLBench: The robot learning benchmark & learning environment","author":"ma","year":"2020","journal-title":"IEEE l of Robotics and Automation"},{"journal-title":"MT- Opt Continuous multitask robotic reinforcement learning at scale","year":"2021","author":"kalashnikov","key":"ref17"},{"key":"ref18","article-title":"Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning","author":"kostrikov","year":"0","journal-title":"International Conference on Learning Representations"},{"journal-title":"Image augmentation is all you need Regularizing deep reinforcement learning from pixels","year":"2020","author":"kostrikov","key":"ref19"},{"key":"ref4","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Intl Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5652494"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197101"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2974093"},{"key":"ref5","first-page":"477","article-title":"Learning 6-dof grasping and pick-place using attention focus","author":"gualtieri","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"journal-title":"Soft actor-critic algorithms and applications","year":"2018","author":"haarnoja","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref2","article-title":"Volumetric grasping network: Real-time 6 dof grasp detection in clutter","author":"breyer","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"3533","DOI":"10.1109\/LRA.2020.2977835","article-title":"Learning one-shot imitation from humans without humans","volume":"5","author":"alessandro","year":"2020","journal-title":"IEEE l of Robotics and Automation"},{"key":"ref9","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1068\/p2935"},{"key":"ref22","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"International Conference on Learning Representations"},{"journal-title":"Ivy Templated deep learning for interframework portability","year":"2021","author":"lenton","key":"ref21"},{"key":"ref42","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","author":"zeng","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"volodymyr","year":"2015","journal-title":"Nature"},{"journal-title":"Improving sample efficiency in model-free reinforcement learning from images","year":"2019","author":"yarats","key":"ref41"},{"key":"ref23","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","author":"matas","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref25","article-title":"Robot spatial perception by stereoscopic vision and 3D evidence grids","author":"moravec","year":"1996","journal-title":"Perception"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2022,6,18]]},"location":"New Orleans, LA, USA","end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09878928.pdf?arnumber=9878928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:59:00Z","timestamp":1665781140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9878928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/cvpr52688.2022.01337","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}