{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:27:07Z","timestamp":1730204827862,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"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":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992874","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"777-782","source":"Crossref","is-referenced-by-count":0,"title":["Value-function estimation and uncertainty propagation in Reinforcement Learning: a Koopman operator approach"],"prefix":"10.1109","author":[{"given":"Francesco","family":"Zanini","sequence":"first","affiliation":[{"name":"University of Padova,Department of Information Engineering,Padova,Italy"}]},{"given":"Alessandro","family":"Chiuso","sequence":"additional","affiliation":[{"name":"University of Padova,Department of Information Engineering,Padova,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-019-09426-y"},{"key":"ref5","article-title":"Sample complexity of linear quadratic gaussian (lqg) control for output feedback systems","author":"Zheng","year":"2021","journal-title":"L4DC"},{"key":"ref6","first-page":"3036","article-title":"The gap between model-based and model-free methods on the linear quadratic regulator: An asymptotic viewpoint","volume-title":"Proceedings of the Thirty-Second Conference on Learning Theory, volume 99 of Proceedings of Machine Learning Research","author":"Tu"},{"key":"ref7","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning","volume":"48","author":"Gu"},{"key":"ref8","first-page":"5694","article-title":"Imagination-augmented agents for deep reinforcement learning","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Racani\u00e8re"},{"key":"ref9","article-title":"Model-based value estimation for efficient model-free reinforcement learning","author":"Feinberg","year":"2018","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28650-9_4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.08.441"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.17.5.315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-35713-9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683220"},{"key":"ref15","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Advances in Neural Information Processing Systems","volume":"12","author":"Sutton","year":"1999"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/2200000036"},{"key":"ref17","article-title":"Gpytorch: Blackbox matrix-matrix gaussian process inference with GPU acceleration","author":"Gardner","year":"2018","journal-title":"CoRR"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","start":{"date-parts":[[2022,12,6]]},"location":"Cancun, Mexico","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992874.pdf?arnumber=9992874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T09:32:04Z","timestamp":1709371924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992874\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992874","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}