{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:38:33Z","timestamp":1730266713133,"version":"3.28.0"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650992","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Offline Reinforcement Learning via Dynamics-Aware Mixup"],"prefix":"10.1109","author":[{"given":"Chang","family":"Tan","sequence":"first","affiliation":[{"name":"Jilin University,College of Software,Changchun,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjie","family":"Su","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"international conference on machine learning","author":"Agarwal","key":"ref1"},{"key":"ref2","first-page":"18 353","article-title":"Bail: Best-action imitation learning for batch deep reinforcement learning","volume":"33","author":"Chen","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"The essential elements of offline rl via supervised learning","volume-title":"Int. Conf. on Learning Representations","author":"Emmons","key":"ref3"},{"journal-title":"Secant: Self-expert cloning for zero-shot generalization of visual policies","year":"2021","author":"Fan","key":"ref4"},{"journal-title":"D4rl: Datasets for deep data-driven reinforcement learning","year":"2020","author":"Fu","key":"ref5"},{"key":"ref6","first-page":"20 132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in neural information processing systems"},{"article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"international conference on machine learning","author":"Fujimoto","key":"ref7"},{"key":"ref8","first-page":"449","article-title":"Model-based offline reinforcement learning with pessimism-modulated dynamics belief","volume":"35","author":"Guo","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1142\/p341"},{"key":"ref11","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on Robot Learning","author":"Kalashnikov"},{"key":"ref12","first-page":"21 810","article-title":"Morel: Model-based offline reinforcement learning","volume":"33","author":"Kidambi","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"International Conference on Machine Learning","author":"Kostrikov"},{"journal-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","year":"2019","author":"Kumar","key":"ref14"},{"key":"ref15","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":"ref16","article-title":"Reinforcement learning with augmented data","author":"Laskin","year":"2020","journal-title":"neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref18","first-page":"19 884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"Laskin","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Representation balancing offline model-based reinforcement learning","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Lee","key":"ref19"},{"journal-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","year":"2020","author":"Levine","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"journal-title":"Revisiting design choices in model-based offline reinforcement learning","year":"2021","author":"Lu","key":"ref22"},{"key":"ref23","first-page":"38 218","article-title":"Double check your state before trusting it: Confidence-aware bidirectional offline model-based imagination","volume":"35","author":"Lyu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Deployment-efficient reinforcement learning via model-based offline optimization","year":"2020","author":"Matsushima","key":"ref24"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref25"},{"journal-title":"Algaedice: Policy gradient from arbitrary experience","year":"2019","author":"Nachum","key":"ref26"},{"journal-title":"Awac: Accelerating online reinforcement learning with offline datasets","year":"2020","author":"Nair","key":"ref27"},{"journal-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","year":"2021","author":"Peng","key":"ref28"},{"key":"ref29","first-page":"17 811","article-title":"Offline meta-reinforcement learning with online self-supervision","volume-title":"International Conference on Machine Learning","author":"Pong"},{"journal-title":"A survey on offline reinforcement learning: Taxonomy, review, and open problems","year":"2022","author":"Prudencio","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref32","first-page":"16 082","article-title":"Rambo-rl: Robust adversarial model-based offline reinforcement learning","volume":"35","author":"Rigter","year":"2022","journal-title":"Advances in neural information processing systems"},{"journal-title":"d3rlpy: An offline deep reinforcement learning library","year":"2021","author":"Seno","key":"ref33"},{"journal-title":"Keep doing what worked: Behavioral modelling priors for offline reinforcement learning","year":"2020","author":"Siegel","key":"ref34"},{"journal-title":"Cog: Connecting new skills to past experience with offline reinforcement learning","year":"2020","author":"Singh","key":"ref35"},{"article-title":"S4rl: Surprisingly simple self-supervision for offline reinforcement learning in robotics","year":"2022","author":"Sinha","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191211"},{"article-title":"Reinforcement learning: An introduction. cambridge, ma, usa: A bradford book","year":"2018","author":"Sutton","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref40","first-page":"29 420","article-title":"Offline reinforcement learning with reverse model-based imagination","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","first-page":"7968","article-title":"Improving generalization in reinforcement learning with mixture regularization","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Behavior regularized offline reinforcement learning","year":"2019","author":"Wu","key":"ref42"},{"article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","volume-title":"international conference on machine learning","author":"Wu","key":"ref43"},{"key":"ref44","first-page":"17 216","article-title":"A unified framework for alternating offline model training and policy learning","volume":"35","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","first-page":"28 954","article-title":"Combo: Conservative offline model-based policy optimization","volume":"34","author":"Yu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref46","first-page":"14 129","article-title":"Mopo: Model-based offline policy optimization","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Learning invariant representations for reinforcement learning without reconstruction","year":"2020","author":"Zhang","key":"ref47"},{"journal-title":"mixup: Beyond empirical risk minimization","year":"2017","author":"Zhang","key":"ref48"},{"journal-title":"robosuite: A modular simulation framework and benchmark for robot learning","year":"2020","author":"Zhu","key":"ref49"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650992.pdf?arnumber=10650992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:23:54Z","timestamp":1725949434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650992","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}