{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T10:46:12Z","timestamp":1778496372960,"version":"3.51.4"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"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":[[2023,12,5]]},"DOI":"10.1109\/ssci52147.2023.10372067","type":"proceedings-article","created":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T14:30:22Z","timestamp":1704119422000},"page":"1429-1434","source":"Crossref","is-referenced-by-count":1,"title":["Uncertainty Quantification for Efficient and Risk-Sensitive Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Mohamed-Harith","family":"Ibrahim","sequence":"first","affiliation":[{"name":"Univ. Clermont Auvergne, CNRS, UMR,Mines Saint-Etienne,Saint-Etienne,France,F-42023"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"St\u00e9phane","family":"Lecoeuche","sequence":"additional","affiliation":[{"name":"IMT Nord Europe, Institut Mines-Telecom, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacques","family":"Boonaert","sequence":"additional","affiliation":[{"name":"IMT Nord Europe, Institut Mines-Telecom, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mireille","family":"Batton-Hubert","sequence":"additional","affiliation":[{"name":"Univ. Clermont Auvergne, CNRS, UMR,Mines Saint-Etienne,Saint-Etienne,France,F-42023"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garcia","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21959"},{"key":"ref5","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Bellemare","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref7","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"International conference on machine learning","author":"Dabney","year":"2018"},{"key":"ref8","article-title":"Distributed distributional deterministic policy gradients","author":"Barth-Maron","year":"2018","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Worst cases policy gradients","author":"Tang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"958","article-title":"Improving robustness via risk averse distributional reinforcement learning","author":"Singh","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref11","article-title":"Risk-averse offline reinforcement learning","author":"Urp\u00ed","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Dsac: Distributional soft actor critic for risk-sensitive reinforcement learning","author":"Ma","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Ucb exploration via q-ensembles","author":"Chen","year":"2017","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"6131","article-title":"Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Lee","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6036"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"ref17","article-title":"Uncertaintyaware reinforcement learning for collision avoidance","author":"Kahn","year":"2017","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Deep exploration via bootstrapped dqn","volume":"29","author":"Osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Randomized ensembled double q-learning: Learning fast without a model","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Dropout q-functions for doubly efficient reinforcement learning","author":"Hiraoka","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Estimating risk and uncertainty in deep reinforcement learning","author":"Clements","year":"2019","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"631","article-title":"Sentinel: taming uncertainty with ensemble based distributional reinforcement learning","volume-title":"Uncertainty in Artificial Intelligence","author":"Eriksson","year":"2022"},{"key":"ref23","first-page":"20218","article-title":"Uncertainty-aware reinforcement learning for risk-sensitive player evaluation in sports game","volume":"35","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892771"},{"key":"ref25","article-title":"Noisy networks for exploration","author":"Fortunato","year":"2017","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4266(02)00262-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref28","article-title":"Gymnasium","author":"Towers","year":"2023"}],"event":{"name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Mexico City, Mexico","start":{"date-parts":[[2023,12,5]]},"end":{"date-parts":[[2023,12,8]]}},"container-title":["2023 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10371778\/10371788\/10372067.pdf?arnumber=10372067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T18:52:20Z","timestamp":1705085540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10372067\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ssci52147.2023.10372067","relation":{},"subject":[],"published":{"date-parts":[[2023,12,5]]}}}