{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T23:18:01Z","timestamp":1769555881633,"version":"3.49.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561692","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"14291-14297","source":"Crossref","is-referenced-by-count":16,"title":["What Can I Do Here? Learning New Skills by Imagining Visual Affordances"],"prefix":"10.1109","author":[{"given":"Alexander","family":"Khazatsky","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashvin","family":"Nair","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Jing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref33","article-title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","author":"stadie","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref32","article-title":"Learning Structured Output Representation using Deep Conditional Generative Models","author":"sohn","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref30","first-page":"1312","article-title":"Universal Value Function Approximators","author":"schaul","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref37","article-title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","author":"warde-farley","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref36","first-page":"6307","article-title":"Neural Discrete Representation Learning","volume":"2017 decem","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref35","first-page":"4797","article-title":"Conditional Image Generation with PixelCNN Decoders","author":"van den oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","author":"tang","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref10","article-title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","author":"finn","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref11","author":"gibson","year":"1979","journal-title":"The Ecological Approach to Visual Perception"},{"key":"ref12","article-title":"Generative Adversarial Nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref13","article-title":"Automatic Goal Generation for Reinforcement Learning Agents","author":"held","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref14","article-title":"Variational Information Maximizing Exploration","author":"houthooft","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref15","article-title":"Auto-Encoding Variational Bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref16","first-page":"83","article-title":"Policy search for motor primitives in robotics","volume":"97","author":"kober","year":"2008","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref17","first-page":"611","article-title":"Machine Learning for Fast Quadrupedal Locomotion","author":"kohl","year":"2004","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref18","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref19","first-page":"1334","article-title":"End-to-End Training of Deep Visuomotor Policies","volume":"17","author":"levine","year":"2016","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref28","article-title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","author":"pong","year":"2020","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(97)00043-2"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.008"},{"key":"ref6","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref29","article-title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","author":"rakelly","year":"2019","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref5","author":"berger","year":"2014","journal-title":"The Developing Person Through the Life Span"},{"key":"ref8","article-title":"Adversarial Feature Learning","author":"donahue","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref7","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2019","journal-title":"The Association for Computational Linguistics (ACL"},{"key":"ref2","article-title":"Hindsight Experience Replay","author":"andrychowicz","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref9","author":"duan","year":"2016","journal-title":"RL$^2$ Fast Reinforcement Learning via Slow Reinforcement Learning"},{"key":"ref1","article-title":"Learning to Poke by Poking: Experiential Learning of Intuitive Physics","author":"agrawal","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref20","article-title":"Learning Latent Plans from Play","author":"lynch","year":"2019","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref22","article-title":"Data-Efficient Hierarchical Reinforcement Learning","author":"nachum","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref21","first-page":"1","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013","journal-title":"NIPS Workshop on Deep Learning"},{"key":"ref24","article-title":"Accelerating Online Reinforcement Learning with Offline Datasets","author":"nair","year":"2020"},{"key":"ref23","article-title":"Contextual Imagined Goals for Self-Supervised Robotic Learning","author":"nair","year":"2019","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref25","article-title":"Visual Reinforcement Learning with Imagined Goals","author":"nair","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561692.pdf?arnumber=9561692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:50:03Z","timestamp":1673563803000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561692\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561692","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}