{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:08:23Z","timestamp":1759133303251,"version":"3.44.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8967559","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"7680-7687","source":"Crossref","is-referenced-by-count":11,"title":["Learning Real-World Robot Policies by Dreaming"],"prefix":"10.1109","author":[{"given":"Aj","family":"Piergiovanni","sequence":"first","affiliation":[{"name":"Computing Engineering Indiana University Bloomington,School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alan","family":"Wu","sequence":"additional","affiliation":[{"name":"Computing Engineering Indiana University Bloomington,School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael S.","family":"Ryoo","sequence":"additional","affiliation":[{"name":"Computing Engineering Indiana University Bloomington,School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref32","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"christiano","year":"2016","journal-title":"arXiv preprint arXiv 1610 09756"},{"key":"ref31","article-title":"Towards adapting deep visuomotor representations from simulated to real environments","author":"tzeng","year":"2015","journal-title":"arXiv 1511 07111"},{"key":"ref30","article-title":"World models","author":"ha","year":"2018","journal-title":"arXiv preprint arXiv 1803 10122"},{"key":"ref35","article-title":"Learning robot activities from first-person human videos using convolutional future regression","author":"lee","year":"2017","journal-title":"IROS"},{"key":"ref34","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref10","article-title":"Ssd: Single shot multibox detector","author":"liu","year":"2016","journal-title":"ECCV"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08864-8_25"},{"key":"ref13","article-title":"Towards vision-based deep reinforcement learning for robotic motion control","author":"zhang","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/s13218-015-0356-1","article-title":"Autonomous learning of state representations for control","author":"b\u00f6hmer","year":"2015","journal-title":"KI-Künstliche Intell"},{"key":"ref17","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"ref19","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref28","article-title":"The predictron: End-to-end learning and planning","author":"silver","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref4","article-title":"From pixels to torques: Policy learning with deep dynamical models","author":"wahlstr\u00f6m","year":"2015","journal-title":"arXiv preprint arXiv 1502 03500"},{"key":"ref27","article-title":"Improved learning of dynamics models for control","author":"venkatraman","year":"2016","journal-title":"International Symposium on Experimental Robotics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref29","article-title":"Value prediction network","author":"oh","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref5","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","author":"levine","year":"2016","journal-title":"arXiv preprint arXiv 1603 02895"},{"key":"ref8","article-title":"Imaginationaugmented agents for deep reinforcement learning","author":"weber","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref2","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref9","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref20","article-title":"Activity forecasting","author":"kitani","year":"2012","journal-title":"ECCV"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.399"},{"key":"ref21","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","author":"xue","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref24","article-title":"Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning","author":"nagabandi","year":"2017","journal-title":"arXiv preprint arXiv 1708 02562"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00278"},{"key":"ref26","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref25","article-title":"Temporal difference models: Model-free deep rl for model-based control","author":"pong","year":"2018","journal-title":"arXiv preprint arXiv 1802 09085"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08967559.pdf?arnumber=8967559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T21:54:25Z","timestamp":1756245265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967559","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}