{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:51:17Z","timestamp":1776783077960,"version":"3.51.2"},"reference-count":35,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561593","type":"proceedings-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T20:28:35Z","timestamp":1634675315000},"page":"10689-10695","source":"Crossref","is-referenced-by-count":19,"title":["Context-Aware Safe Reinforcement Learning for Non-Stationary Environments"],"prefix":"10.1109","author":[{"given":"Baiming","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuxin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiacheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengdi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"2993","article-title":"Optimizing the cvar via sampling","author":"tamar","year":"2015","journal-title":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence"},{"key":"ref32","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"},{"key":"ref31","article-title":"Modeling, identification and control of cart-pole system","author":"pati","year":"2014","journal-title":"Ph D Dissertation"},{"key":"ref30","article-title":"Convolutional conditional neural processes","author":"gordon","year":"2019"},{"key":"ref35","article-title":"Projection-based constrained policy optimization","author":"yang","year":"2020","journal-title":"ICLRE"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197411"},{"key":"ref10","article-title":"Constrained policy optimization","author":"achiam","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"ref12","first-page":"8092","article-title":"A lyapunov-based approach to safe reinforcement learning","author":"chow","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018"},{"key":"ref14","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017"},{"key":"ref15","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"2018"},{"key":"ref16","article-title":"Task-agnostic online reinforcement learning with an infinite mixture of gaussian processes","author":"xu","year":"2020"},{"key":"ref17","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s001860050035"},{"key":"ref28","article-title":"Attentive neural processes","author":"kim","year":"2019"},{"key":"ref4","article-title":"Delay-aware modelbased reinforcement learning for continuous control","author":"chen","year":"2020"},{"key":"ref27","article-title":"Neural processes","author":"garnelo","year":"2018"},{"key":"ref3","article-title":"Deep online learning via metalearning: Continual adaptation for model-based rl","author":"nagabandi","year":"2018"},{"key":"ref6","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref29","article-title":"Recurrent attentive neural process for sequential data","author":"qin","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref8","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref2","first-page":"2","article-title":"Alphastar: Mastering the real-time strategy game starcraft ii","author":"vinyals","year":"2019","journal-title":"DeepMind blog"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref1","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":"ref20","article-title":"Lyapunov-based safe policy optimization for continuous control","author":"chow","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2949757"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref24","article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016"},{"key":"ref23","first-page":"9797","article-title":"Safe reinforcement learning in constrained markov decision processes","author":"wachi","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref26","article-title":"Non-stationary reinforcement learning: The blessing of (more) optimism","author":"cheung","year":"2019","journal-title":"Available at SSRN 3397818"},{"key":"ref25","article-title":"Meta reinforcement learning with latent variable gaussian processes","author":"s\u00e6mundsson","year":"2018"}],"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\/09561593.pdf?arnumber=9561593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:47:06Z","timestamp":1652183226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561593","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}