{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:23:29Z","timestamp":1763191409223,"version":"3.45.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228950","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Single Pass Uncertainty Estimation in Q-Learning via Dropout Distillation"],"prefix":"10.1109","author":[{"given":"Nikolaos","family":"Kaparinos","sequence":"first","affiliation":[{"name":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning Group,AIIA Lab. Dept. of Informatics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaos","family":"Passalis","sequence":"additional","affiliation":[{"name":"Aristotle University of Thessaloniki,Dept. of Chemical Engineering,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[{"name":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning Group,AIIA Lab. Dept. of Informatics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289910"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909691"},{"article-title":"Open-sourced reinforcement learning environments for surgical robotics","year":"2019","author":"Richter","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SYSCON.2019.8836924"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3457538"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21959"},{"article-title":"How to enable uncertainty estimation in proximal policy optimization","year":"2022","author":"Bykovets","key":"ref12"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113820"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICSESS47205.2019.9040728"},{"article-title":"Learning from delayed rewards","year":"1989","author":"Watkins","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref18","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Wang"},{"article-title":"Prioritized experience replay","year":"2015","author":"Schaul","key":"ref19"},{"key":"ref20","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Bellemare"},{"article-title":"Efficient exploration with double uncertain value networks","year":"2017","author":"Moerland","key":"ref21"},{"key":"ref22","article-title":"Dropout q-functions for doubly efficient reinforcement learning","volume":"4","author":"Hiraoka","year":"2021"},{"article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","year":"2021","author":"Wu","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1506.02142"},{"key":"ref25","article-title":"Deep exploration via bootstrapped dqn","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"29","author":"Osband"},{"key":"ref26","first-page":"195","article-title":"Uncertainty-driven imagination for continuous deep reinforcement learning","volume-title":"Proceedings of the Conference on Robot Learning","author":"Kalweit"},{"key":"ref27","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified q-ensemble","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"34","author":"An"},{"article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","year":"2022","author":"Bai","key":"ref28"},{"key":"ref29","first-page":"18267","article-title":"Why so pessimistic? estimating uncertainties for offline rl through ensembles, and why their independence matters","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"35","author":"Ghasemipour"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s42354-019-0238-z"},{"article-title":"Dropout distillation for efficiently estimating model confidence","year":"2018","author":"Gurau","key":"ref31"},{"article-title":"Minatar: An atari-inspired testbed for thorough and reproducible reinforcement learning experiments","year":"2019","author":"Young","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.10.005"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228950.pdf?arnumber=11228950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:20:21Z","timestamp":1763191221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228950","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}