{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:30:57Z","timestamp":1730255457609,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561219","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"9935-9942","source":"Crossref","is-referenced-by-count":3,"title":["Double Meta-Learning for Data Efficient Policy Optimization in Non-Stationary Environments"],"prefix":"10.1109","author":[{"given":"Elahe","family":"Aghapour","sequence":"first","affiliation":[{"name":"University of Southern California,Department of Computer Science,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nora","family":"Ayanian","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Computer Science,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref38","article-title":"Neural network dynamics for model-based deep reinforcement learning with model-free finetuning","author":"clavera","year":"2018","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"article-title":"Promp: Proximal meta-policy search","year":"2018","author":"rothfuss","key":"ref33"},{"key":"ref32","article-title":"A simple neural attentive meta-learner","author":"mishra","year":"2018","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref31","article-title":"Learning to reinforcement learn","author":"wang","year":"2017","journal-title":"Cognitive Science Society (CogSci)"},{"key":"ref30","article-title":"Learning to adapt: Meta-learning for model-based control","volume":"3","author":"clavera","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref35","article-title":"Critical learning periods in deep neural networks","author":"achille","year":"2019","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref34","article-title":"Model-based reinforcement learning via meta-policy optimization","author":"clavera","year":"2019","journal-title":"International Conference on Learning Representations (ICRL)"},{"article-title":"Challenges of real-world reinforcement learning","year":"2019","author":"dulac-arnold","key":"ref10"},{"article-title":"Model-based value estimation for efficient model-free reinforcement learning","year":"2018","author":"feinberg","key":"ref40"},{"article-title":"On learning to think: Algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models","year":"2015","author":"schmidhuber","key":"ref11"},{"key":"ref12","article-title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","author":"zintgraf","year":"2020","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref13","article-title":"Rl 2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2017","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref14","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_13"},{"article-title":"Optimization as a model for fewshot learning","year":"2016","author":"ravi","key":"ref16"},{"article-title":"On first-order meta-learning algorithms","year":"2018","author":"nichol","key":"ref17"},{"key":"ref18","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume":"70","author":"finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"How to train your MAML","author":"antoniou","year":"2019","journal-title":"International Conference on Learning Representations (ICRL)"},{"article-title":"Model-based reinforcement learning via meta-policy optimization","year":"2018","author":"clavera","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref27","article-title":"Reinforcement learning in robust markov decision processes","author":"lim","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref6","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref29","article-title":"Continuous adaptation via metalearning in non-stationary and competitive environments","author":"al-shedivat","year":"2018","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref9","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","author":"kamthe","year":"2018","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"article-title":"On first-order meta-learning algorithms","year":"2018","author":"nichol","key":"ref20"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref45"},{"article-title":"Meta-SGD: Learning to learn quickly for few-shot learning","year":"2017","author":"li","key":"ref22"},{"key":"ref21","article-title":"Deep online learning via meta-learning: Continual adaptation for model-based RL","author":"nagabandi","year":"2019","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref24","volume":"40","author":"zhou","year":"1996","journal-title":"Robust and Optimal Control"},{"key":"ref41","article-title":"Model-ensemble trust-region policy optimization","author":"kurutach","year":"2018","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref23","article-title":"Recasting gradient-based meta-learning as hierarchical bayes","author":"grant","year":"2018","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref44","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref26","article-title":"EPOpt: Learning robust neural network policies using model ensembles","author":"rajeswaran","year":"2017","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref43","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref25","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)"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","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\/09561219.pdf?arnumber=9561219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:36:04Z","timestamp":1670283364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561219","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}