{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T03:02:56Z","timestamp":1781665376045,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/lra.2024.3371260","type":"journal-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T18:59:31Z","timestamp":1709146771000},"page":"3918-3925","source":"Crossref","is-referenced-by-count":7,"title":["Data-Efficient Task Generalization via Probabilistic Model-Based Meta Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2469-2841","authenticated-orcid":false,"given":"Arjun","family":"Bhardwaj","sequence":"first","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0129-0540","authenticated-orcid":false,"given":"Jonas","family":"Rothfuss","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6238-9734","authenticated-orcid":false,"given":"Bhavya","family":"Sukhija","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1685-4099","authenticated-orcid":false,"given":"Yarden","family":"As","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-4990","authenticated-orcid":false,"given":"Marco","family":"Hutter","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6604-4784","authenticated-orcid":false,"given":"Stelian","family":"Coros","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7260-9673","authenticated-orcid":false,"given":"Andreas","family":"Krause","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref3","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Deisenroth","year":"2011"},{"key":"ref4","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chua","year":"2018"},{"key":"ref5","first-page":"617","article-title":"Model-based reinforcement learning via meta-policy optimization","volume-title":"Proc. 2nd Annu. Conf. Robot Learn.","author":"Clavera","year":"2018"},{"key":"ref6","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref8","first-page":"14156","article-title":"Efficient model-based reinforcement learning through optimistic policy search and planning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Curi","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2"},{"key":"ref10","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref11","article-title":"MARS: Meta-learning as score matching in the function space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pavasovic","year":"2022"},{"key":"ref12","article-title":"Learning to reinforcement learn","volume-title":"Proc. 39th Annu. Meeting Cogn. Sci. Soc.","author":"Wang","year":"2017"},{"key":"ref13","article-title":"ProMP: Proximal meta-policy search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rothfuss","year":"2019"},{"key":"ref14","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20730"},{"key":"ref16","first-page":"642","article-title":"Meta reinforcement learning with latent variable Gaussian processes","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell.","author":"Smundsson","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5989"},{"key":"ref18","first-page":"5757","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2020"},{"key":"ref19","first-page":"129","article-title":"Meta-model-based meta-policy optimization","volume-title":"Proc. Mach. Learn. Res.","author":"Hiraoka","year":"2021"},{"key":"ref20","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clavera","year":"2019"},{"key":"ref21","first-page":"991","article-title":"A PAC-Bayesian bound for lifelong learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pentina","year":"2014"},{"key":"ref22","first-page":"205","article-title":"Meta-learning by adjusting priors based on extended PAC-Bayes theory","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amit","year":"2018"},{"key":"ref23","first-page":"9116","article-title":"PACOH: Bayes-optimal meta-learning with PAC-guarantees","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rothfuss","year":"2021"},{"key":"ref24","first-page":"237","article-title":"Meta-learning priors for safe Bayesian optimization","volume-title":"Proc. Conf. Robot Learn.","author":"Rothfuss","year":"2023"},{"key":"ref25","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heess","year":"2015"},{"key":"ref26","article-title":"VIME: Variational information maximizing exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Houthooft","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_16"},{"key":"ref28","first-page":"391","article-title":"A primer on PAC-bayesian learning","volume-title":"Proc. SMF 2018: Congrs de la Socit Mathmatique de France","author":"Guedj","year":"2019"},{"key":"ref29","first-page":"681","article-title":"Bayesian learning via stochastic gradient langevin dynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Welling","year":"2011"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref31","first-page":"2378","article-title":"Stein variational gradient descent: A general purpose Bayesian inference algorithm","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2016"},{"key":"ref32","first-page":"746","article-title":"A unified particle-optimization framework for scalable Bayesian sampling","volume-title":"Proc. 24th Conf. Uncertainty Artif. Intell.","author":"Chen","year":"2018"},{"key":"ref33","first-page":"701","article-title":"Reinforcement learning in robust markov decision processes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lim","year":"2013"},{"key":"ref34","first-page":"1049","article-title":"Sample-efficient cross-entropy method for real-time planning","volume-title":"Proc. 4th Conf. Robot Learn.","author":"Pinneri","year":"2020"},{"key":"ref35","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref36","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21977"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161574"},{"key":"ref39","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Janner","year":"2019"},{"issue":"1","key":"ref40","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garca","year":"2015"},{"key":"ref41","article-title":"Constrained policy optimization via Bayesian world models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"As","year":"2022"},{"key":"ref42","article-title":"Planning to explore via self-supervised world models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sekar","year":"2020"},{"key":"ref43","first-page":"38122","article-title":"Optimistic active exploration of dynamical systems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Sukhija","year":"2023"},{"key":"ref44","first-page":"1774","article-title":"Hallucinated adversarial control for conservative offline policy evaluation","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Rothfuss","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11123"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10440130\/10452796.pdf?arnumber=10452796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T21:28:49Z","timestamp":1734989329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10452796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":45,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3371260","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}