{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:41:00Z","timestamp":1759401660514,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"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":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160764","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"7169-7175","source":"Crossref","is-referenced-by-count":6,"title":["Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zheng","family":"Wu","sequence":"first","affiliation":[{"name":"University of California, Berkeley,Berkeley,CA,USA"}]},{"given":"Yichen","family":"Xie","sequence":"additional","affiliation":[{"name":"University of California, Berkeley,Berkeley,CA,USA"}]},{"given":"Wenzhao","family":"Lian","sequence":"additional","affiliation":[{"name":"Intrinsic Innovation LLC,Mountain View,CA,USA"}]},{"given":"Changhao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California, Berkeley,Berkeley,CA,USA"}]},{"given":"Yanjiang","family":"Guo","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Jianyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Stefan","family":"Schaal","sequence":"additional","affiliation":[{"name":"Intrinsic Innovation LLC,Mountain View,CA,USA"}]},{"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"University of California, Berkeley,Berkeley,CA,USA"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Asymmetric actor critic for image-based robot learning","author":"pinto","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref12","first-page":"3803","author":"peng","year":"2018","journal-title":"Sim-to-real transfer of robotic control with dynamics randomization"},{"key":"ref15","first-page":"1126","author":"finn","year":"2017","journal-title":"Model-agnostic meta-learning for fast adaptation of deep networks"},{"key":"ref14","article-title":"R12: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"journal-title":"robosuite A modular simulation framework and benchmark for robot learning","year":"2020","author":"zhu","key":"ref30"},{"key":"ref11","first-page":"23","author":"tobin","year":"2017","journal-title":"Domain randomization for transferring deep neural networks from simulation to the real world"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/wics.101"},{"key":"ref10","first-page":"737","author":"zhao","year":"2020","journal-title":"Sim-to-real transfer in deep reinforcement learning for robotics a survey"},{"key":"ref32","first-page":"1861","author":"haarnoja","year":"2018","journal-title":"Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor"},{"key":"ref2","article-title":"Probabilistic model-agnostic meta-learning","volume":"31","author":"finn","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"2169","author":"devin","year":"2017","journal-title":"Learning modular neural network policies for multi-task and multi-robot transfer"},{"key":"ref17","first-page":"7693","author":"zintgraf","year":"2019","journal-title":"Fast context adaptation via meta-learning"},{"key":"ref16","article-title":"Meta-reinforcement learning of structured exploration strategies","volume":"31","author":"gupta","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"166","author":"andreas","year":"2017","journal-title":"Modular multitask reinforcement learning with policy sketches"},{"key":"ref18","first-page":"9728","author":"schoettler","year":"2020","journal-title":"Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks"},{"key":"ref24","article-title":"Policy archi-tectures for compositional generalization in control","author":"zhou","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref23","first-page":"3418","author":"kipf","year":"2019","journal-title":"Compile Compositional imitation learning and execution"},{"key":"ref26","first-page":"441","author":"zhang","year":"2015","journal-title":"Feature space decomposition for effective robot adaptation"},{"key":"ref25","first-page":"2661","author":"oh","year":"2017","journal-title":"Zero-shot task generalization with multi-task deep reinforcement learning"},{"key":"ref20","first-page":"6244","author":"haarnoja","year":"2018","journal-title":"Deep reinforcement learning for robotic manipulation"},{"key":"ref22","article-title":"Language as an abstraction for hierarchical deep reinforcement learning","volume":"32","author":"jiang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"8565","author":"huang","year":"2019","journal-title":"Neural task graphs Generalizing to unseen tasks from a single video demonstration"},{"key":"ref28","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"tarvainen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","article-title":"Compo-sitional plan vectors","volume":"32","author":"devin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref29","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"grill","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"651","author":"kalashnikov","year":"2018","journal-title":"QT-Opt Scalable deep reinforcement learning for vision-based robotic manipulation"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref7"},{"key":"ref9","first-page":"8943","author":"lee","year":"2019","journal-title":"Making sense of vision and touch Self-supervised learning of multimodal representations for contact-rich tasks"},{"key":"ref4","article-title":"Meld: Meta-reinforcement learning from images via latent state models","author":"zhao","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref3","first-page":"5331","author":"rakelly","year":"2019","journal-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables[J]"},{"key":"ref6","article-title":"Varibad: A very good method for bayes-adaptive deep rl via meta-learning","author":"zintgraf","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"Meta reinforcement learning as task inference","author":"humplik","year":"2019","journal-title":"ArXiv Preprint"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160764.pdf?arnumber=10160764","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:36:37Z","timestamp":1690220197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160764\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160764","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}