{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,11]],"date-time":"2025-05-11T04:01:30Z","timestamp":1746936090862,"version":"3.40.5"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"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":[[2025,3,24]]},"DOI":"10.1109\/wcnc61545.2025.10978817","type":"proceedings-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T17:53:33Z","timestamp":1746813213000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Cosine Similarity Based Adaptive Implicit Q-Learning for Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xinchen","family":"Han","sequence":"first","affiliation":[{"name":"Samovar, Télécom SudParis Institut Polytechnique de Paris,Paris,France"}]},{"given":"Hossam","family":"Afifi","sequence":"additional","affiliation":[{"name":"Samovar, Télécom SudParis Institut Polytechnique de Paris,Paris,France"}]},{"given":"Michel","family":"Marot","sequence":"additional","affiliation":[{"name":"Samovar, Télécom SudParis Institut Polytechnique de Paris,Paris,France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650450"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2200253"},{"volume-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","year":"2020","author":"Levine","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref5","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273590"},{"key":"ref7","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111101"},{"key":"ref11","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"},{"volume-title":"Projection implicit q-learning with support constraint for offline reinforcement learning","year":"2025","author":"Han","key":"ref12"},{"key":"ref13","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified q-ensemble","volume":"34","author":"An","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"18267","article-title":"Why so pessimistic? estimating uncertainties for offline rl through ensembles, and why their independence matters","volume":"35","author":"Ghasemipour","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"4933","article-title":"Offline rl without off-policy evaluation","volume":"34","author":"Brandfonbrener","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Offline rl with no ood actions: In-sample learning via implicit value regularization","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"volume-title":"Behavior regularized offline reinforcement learning","year":"2019","author":"Wu","key":"ref18"},{"key":"ref19","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning","author":"Fujimoto","year":"2019"},{"key":"ref20","first-page":"36902","article-title":"Lapo: Latent-variable advantage-weighted policy optimization for offline reinforcement learning","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","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":"ref22","first-page":"23829","article-title":"Supported trust region optimization for offline reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Mao","year":"2023"},{"key":"ref23","article-title":"Reinforcement learning: An introduction","volume-title":"A Bradford Book","author":"Sutton","year":"2018"},{"key":"ref24","article-title":"Rvs: What is essential for offline rl via supervised learning?","author":"Emmons","year":"2021","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"4085","article-title":"A policy-guided imitation approach for offline reinforcement learning","volume":"35","author":"Xu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Reinformer: Max-return sequence modeling for offline rl","year":"2024","author":"Zhuang","key":"ref26"}],"event":{"name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","start":{"date-parts":[[2025,3,24]]},"location":"Milan, Italy","end":{"date-parts":[[2025,3,27]]}},"container-title":["2025 IEEE Wireless Communications and Networking Conference (WCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10978109\/10978116\/10978817.pdf?arnumber=10978817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:00:32Z","timestamp":1746856832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10978817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/wcnc61545.2025.10978817","relation":{},"subject":[],"published":{"date-parts":[[2025,3,24]]}}}