{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:46:55Z","timestamp":1730270815217,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981621","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T14:38:15Z","timestamp":1672065495000},"page":"8987-8994","source":"Crossref","is-referenced-by-count":0,"title":["Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularization"],"prefix":"10.1109","author":[{"given":"Lu","family":"Wen","sequence":"first","affiliation":[{"name":"Mechanical Engineering, University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ford Research and Advanced Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H. Eric","family":"Tseng","sequence":"additional","affiliation":[{"name":"Ford Research and Advanced Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baljeet","family":"Singh","sequence":"additional","affiliation":[{"name":"Ford Research and Advanced Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitar","family":"Filev","sequence":"additional","affiliation":[{"name":"Ford Research and Advanced Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huei","family":"Peng","sequence":"additional","affiliation":[{"name":"Mechanical Engineering, University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Meta-Learning from Few-Shot Learning to Rapid Reinforcement Learning","year":"2019","author":"levine","key":"ref13"},{"key":"ref12","article-title":"Rl 2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Guided meta-policy search","author":"mendonca","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564972"},{"key":"ref11","first-page":"18860","article-title":"Task-robust modelagnostic meta-learning","volume":"33","author":"collins","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"1","article-title":"Weakly-convex-concave min-max optimization: provable algorithms and applications in machine learning","author":"rafique","year":"2021","journal-title":"Optimization Methods and Software"},{"key":"ref2","article-title":"Learning to reinforcement learn","author":"wang","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Composing meta-policies for autonomous driving using hierarchical deep reinforcement learning","author":"liaw","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Model-based adversarial meta-reinforcement learning","author":"lin","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057046"},{"key":"ref19","article-title":"Meta-q-learning","author":"fakoor","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Meta-reinforcement learning of structured exploration strategies","author":"gupta","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref23","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00084"},{"key":"ref25","article-title":"Meta-adversarial inverse re-inforcement learning for decision-making tasks","author":"wang","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref20","article-title":"Improving generalization in meta reinforcement learning using learned objectives","author":"kirsch","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Deep variational information bottleneck","author":"alemi","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Online meta-critic learning for off-policy actor-critic methods","author":"zhou","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2004.12.003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294262"},{"key":"ref7","first-page":"1437","article-title":"A comprehensive survey on safe rein-forcement learning","volume":"16","author":"garcia","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","article-title":"Adversarial attacks on graph neural networks via meta learning","author":"zugner","year":"2019","journal-title":"ArXiv Preprint"},{"journal-title":"How to train your maml","year":"2019","author":"antoniou","key":"ref4"},{"key":"ref3","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref6","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"On first-order meta-learning algorithms","author":"nichol","year":"2018","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981621.pdf?arnumber=9981621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T14:57:07Z","timestamp":1701269827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981621","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}