{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T15:16:32Z","timestamp":1750173392026,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534316","type":"proceedings-article","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T20:40:52Z","timestamp":1632256852000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Adversarial Training for Meta Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Shiqi","family":"Chen","sequence":"first","affiliation":[]},{"given":"Zhengyu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Meta-reinforcement learning robust to distributional shift via model identification and experience relabelina[J]","author":"mendonca","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"A simple neural attentive mera-Iearner[J]","author":"mishra","year":"2017","journal-title":"arXiv nrenrint"},{"key":"ref12","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning[J]","author":"nagabandi","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Robust deep reinforcement learning with adversarial attacks[J]","author":"pattanaik","year":"2017","journal-title":"arXiv nrenrint"},{"journal-title":"Markov decision processes discrete stochastic dynamic nroarammina[M]","year":"2014","author":"puterman","key":"ref14"},{"key":"ref15","article-title":"Promp: Proximal meta-policy search[J]","author":"rothfuss","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Meta reinforcement learning with latent variable gaussian processes[J]","author":"sannundsson","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimizationf [C]","author":"schulman","year":"2015","journal-title":"lnternational conference on machine Iearninz"},{"journal-title":"Reinforcement learning An introduction[M]","year":"2018","author":"sutton","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref28","article-title":"Multi-Initialization Meta-learning With Domain Adaptation[C]","author":"chen","year":"0","journal-title":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref4","article-title":"Levine S. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks [C]","author":"finn","year":"2017","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207265"},{"key":"ref3","article-title":"RI2: Fast reinforcement learning via slow reinforcement learning[7]","author":"duan","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Adversarial attacks on neural network policies[J]","author":"huang","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"Explaining and harnessing adversarial examples[J]","author":"goodfellow","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.29007\/25x3"},{"key":"ref7","article-title":"Delving into adversarial attacks on deep policies[J]","author":"kos","year":"2017","journal-title":"arXiv nreprint"},{"key":"ref2","first-page":"1432","article-title":"Hidden parameter markov decision processes: A semiparametric regression approach for discovering latent task parametrizations[C]","author":"doshi-velez","year":"2016","journal-title":"IJCAI proceedings of the conference NIH Public Access"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140444"},{"key":"ref20","article-title":"Learning to reinforcement learn[J]","author":"wang","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Adversarial meta-Iearning[J]","author":"yin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning[J]","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref24","first-page":"7974","article-title":"Policy teaching via environment poisoning: Training-time adversarial attacks against reinforcement learning [C]","author":"rakhsha","year":"2020","journal-title":"Int Conference on Machine Learning"},{"journal-title":"Generating adversarial examples with adversarial networks","year":"0","author":"xiao","key":"ref23"},{"key":"ref26","article-title":"Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning[J]","author":"yan","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Robust few-shot learning with adversarially queried meta-Iearners[J]","author":"goldblum","year":"2019","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534316.pdf?arnumber=9534316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:46:04Z","timestamp":1652197564000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534316","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}