{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:49:52Z","timestamp":1779101392420,"version":"3.51.4"},"reference-count":21,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650768","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":1,"title":["Conservative In-Distribution Q-Learning for Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zhengdao","family":"Shao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liansheng","family":"Zhuang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Yan","sequence":"additional","affiliation":[{"name":"Step.ai,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liting","family":"Chen","sequence":"additional","affiliation":[{"name":"McGill University,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref2","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref3","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov"},{"key":"ref4","article-title":"Offline RL with no OOD actions: In-sample learning via implicit value regularization","volume-title":"The Eleventh International Conference on Learning Representations","author":"Xu"},{"key":"ref5","article-title":"State advantage weighting for offline rl","author":"Lyu","year":"2022"},{"key":"ref6","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Kumar"},{"key":"ref7","article-title":"Conservative q-learning for offline reinforcement learning","volume":"abs\/2006.04779","author":"Kumar","year":"2020","journal-title":"CoRR"},{"key":"ref8","article-title":"Advantage weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2020"},{"key":"ref9","first-page":"28954","article-title":"Combo: Conservative offline model-based policy optimization","volume-title":"Advances in neural information processing systems","volume":"34","author":"Yu"},{"key":"ref10","first-page":"8591","article-title":"A closer look at offline rl agents","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Fu"},{"key":"ref11","article-title":"Idql: Implicit q-learning as an actor-critic method with diffusion policies","volume":"abs\/2304.10573","author":"Hansen-Estruch","year":"2023"},{"key":"ref12","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref13","article-title":"Efficient and accurate estimation of lipschitz constants for deep neural networks","author":"Fazlyab","year":"2023"},{"key":"ref14","article-title":"Lipschitz constant estimation of neural networks via sparse polynomial optimization","author":"Latorre","year":"2020"},{"key":"ref15","article-title":"Evaluating the robustness of neural networks: An extreme value theory approach","author":"Weng","year":"2018"},{"key":"ref16","article-title":"Lipschitz continuity in model-based reinforcement learning","author":"Asadi","year":"2018"},{"key":"ref17","article-title":"Rorl: Robust offline reinforcement learning via conservative smoothing","author":"Yang","year":"2022"},{"key":"ref18","article-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury","year":"2018"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017"},{"key":"ref20","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Advances in neural information processing systems","volume":"34","author":"Fujimoto"},{"key":"ref21","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Bai"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"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\/10650768.pdf?arnumber=10650768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:58:38Z","timestamp":1725947918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650768\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650768","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}