{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:25:02Z","timestamp":1767338702861,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095236","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["MEET: A Monte Carlo Exploration-Exploitation Trade-Off for Buffer Sampling"],"prefix":"10.1109","author":[{"given":"Julius","family":"Ott","sequence":"first","affiliation":[{"name":"Infineon Technologies AG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Servadei","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Arjona-Medina","sequence":"additional","affiliation":[{"name":"Johannes Kepler University Linz"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrico","family":"Rinaldi","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gianfranco","family":"Mauro","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniela S\u00e1nchez","family":"Lopera","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Stephan","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Stadelmayer","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avik","family":"Santra","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Wille","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Prioritized Sequence Experience Replay","volume":"abs 1905 12726","author":"brittain","year":"2019","journal-title":"CoRR"},{"key":"ref12","article-title":"Prioritized experience replay","volume":"abs 1511 5952","author":"schaul","year":"2016","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.11.006"},{"key":"ref14","article-title":"RUDDER: Return Decomposition for Delayed Rewards","volume":"32","author":"arjona-medina","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"article-title":"Information-directed exploration for deep reinforcement learning","year":"0","author":"nikolov","key":"ref2"},{"key":"ref1","first-page":"3061","article-title":"Revisiting Fundamentals of Experience Replay","author":"fedus","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref17","volume":"34","author":"an","year":"2021","journal-title":"Uncertainty-based offline reinforcement learning with diversified q-ensemble"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/589"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"ref18","first-page":"arxiv","article-title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","author":"mai","year":"2022","journal-title":"ArXiv e-prints"},{"key":"ref24","first-page":"8626","article-title":"Randomized Prior Functions for Deep Reinforcement Learning","author":"osband","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref23","first-page":"5580","article-title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","author":"kendall","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref26","first-page":"282","author":"kocsis","year":"2006","journal-title":"European Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref20","first-page":"195","article-title":"Uncertainty-driven imagination for continuous deep reinforcement learning","author":"kalweit","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref22","article-title":"Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty under Dataset Shift","volume":"32","author":"ovadia","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref28","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref27","first-page":"397","article-title":"Using Confidence Bounds for Exploitation-Exploration Trade-Offs","volume":"3","author":"auer","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","first-page":"1861","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref7","first-page":"2829","article-title":"Continuous Deep Q-Learning with Model-based Acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref9"},{"key":"ref4","first-page":"4033","author":"osband","year":"2016","journal-title":"Deep Exploration via Boot-strapped DQN"},{"key":"ref3","first-page":"522","article-title":"Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning","author":"sedlmeier","year":"2022","journal-title":"International Conference on Agents and Artificial Intelligence (ICAART)"},{"key":"ref6","article-title":"Continuous Control with Deep Reinforcement Learning","author":"lillicrap","year":"2016","journal-title":"4th International Conference on Learning Representations ICLR"},{"key":"ref5","first-page":"387","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095236.pdf?arnumber=10095236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:01:49Z","timestamp":1700506909000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095236","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}