{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T04:04:14Z","timestamp":1725768254520},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"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":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683009","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"2963-2968","source":"Crossref","is-referenced-by-count":3,"title":["Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach"],"prefix":"10.1109","author":[{"given":"Xiaowu","family":"Sun","sequence":"first","affiliation":[{"name":"University of California,Department of Electrical Engineering and Computer Science,Irvine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wael","family":"Fatnassi","sequence":"additional","affiliation":[{"name":"University of California,Department of Electrical Engineering and Computer Science,Irvine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulices Santa","family":"Cruz","sequence":"additional","affiliation":[{"name":"University of California,Department of Electrical Engineering and Computer Science,Irvine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasser","family":"Shoukry","sequence":"additional","affiliation":[{"name":"University of California,Department of Electrical Engineering and Computer Science,Irvine"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"On the number of response regions of deep feed forward networks with piece-wise linear activations","year":"2013","author":"pascanu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683009"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2461328.2461373"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3302504.3311808"},{"key":"ref4","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"article-title":"Meta-learning in neural networks: A survey","year":"2020","author":"hospedales","key":"ref3"},{"article-title":"Provably convergent policy gradient methods for model-agnostic meta-reinforcement learning","year":"2020","author":"fallah","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3205651.3208249"},{"article-title":"Provably correct training of neural network controllers using reachability analysis","year":"2021","author":"sun","key":"ref8"},{"key":"ref7","first-page":"4061","article-title":"Taming maml: Efficient unbiased meta-reinforcement learning","author":"liu","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref2","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","author":"franceschi","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2712906"},{"article-title":"Gaussian processes for machine learning","year":"2006","author":"rasmussen","key":"ref9"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2021,12,14]]},"location":"Austin, TX, USA","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683009.pdf?arnumber=9683009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T20:25:24Z","timestamp":1654547124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683009\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683009","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}