{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:25:33Z","timestamp":1730265933568,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191211","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Uncertainty-Aware Data Augmentation for Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yunjie","family":"Su","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilun","family":"Kong","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"janner","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Reinforcement learning: An introduction","author":"sutton","year":"2018","journal-title":"A Bradford Book"},{"key":"ref12","article-title":"Adversarial attacks on neural network policies","author":"huang","year":"2017","journal-title":"ArXiv Preprint"},{"journal-title":"S4rl Surprisingly simple self-supervision for offline reinforcement learning in robotics","year":"2022","author":"sinha","key":"ref34"},{"key":"ref15","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16973"},{"key":"ref36","article-title":"Single-model uncertainties for deep learning","volume":"32","author":"tagasovska","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"d3rlpy: An offline deep reinforcement learning library","author":"seno","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref30","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"rajeswaran","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294407"},{"key":"ref33","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":"ref10","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":"In International Conference on Machine Learning"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmen-tation for deep learning","volume":"6","author":"shorten","year":"2019","journal-title":"Journal Of Big Data"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2008.06.020"},{"key":"ref1","first-page":"18353","article-title":"Bail: Best-action imitation learning for batch deep reinforcement learning","volume":"33","author":"chen","year":"2020","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"ref17","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Behavior regularized offline reinforcement learning","author":"wu","year":"2019","journal-title":"arXiv Learning"},{"key":"ref16","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","volume":"30","author":"kendall","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"23645","article-title":"Koopman q-learning: Offline reinforcement learning via symmetries of dynamics","author":"weissenbacher","year":"0","journal-title":"In International Conference on Machine Learning"},{"key":"ref19","first-page":"5639","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"laskin","year":"0","journal-title":"In International Conference on Machine Learning"},{"key":"ref18","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"kumar","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"3932","article-title":"Ad-versarially robust policy learning: Active construction of physically-plausible perturbations","author":"mandlekar","year":"0","journal-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI44817.2019.9002856"},{"key":"ref45","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"zhu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"Risk versus uncertainty in deep learning: Bayes, bootstrap and the dangers of dropout","volume":"192","author":"osband","year":"0","journal-title":"Workshop on Bayesian Deep Learning NIPS"},{"key":"ref25","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref20","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"laskin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref42","first-page":"28954","article-title":"Combo: Conservative offline model-based policy optimization","volume":"34","author":"yu","year":"2021","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"ref41","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","author":"wu","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref44","article-title":"Learning invariant representations for reinforcement learning without reconstruction","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/514"},{"key":"ref28","first-page":"17811","article-title":"Offline meta-reinforcement learning with online self-supervision","author":"pong","year":"0","journal-title":"In International Conference on Machine Learning"},{"key":"ref27","article-title":"Randomized prior functions for deep reinforcement learning","volume":"31","author":"osband","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"A survey on offline reinforcement learning: Taxonomy, review, and open problems","author":"prudencio","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref8","first-page":"1050","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"0","journal-title":"In International Conference on Machine Learning"},{"key":"ref7","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref9","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"fu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"The essential elements of offline rl via supervised learning","author":"emmons","year":"0","journal-title":"Int Conf on Learning Representations"},{"key":"ref6","first-page":"1587","article-title":"Addressing function approxi-mation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"In International Conference on Machine Learning"},{"key":"ref5","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"fujimoto","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref40","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","author":"wu","year":"2021","journal-title":"ArXiv Preprint"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191211.pdf?arnumber=10191211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:45:40Z","timestamp":1692639940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191211","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}