{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:41:31Z","timestamp":1730266891951,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651374","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Delayed MDPs with Feature Mapping"],"prefix":"10.1109","author":[{"given":"Jialin","family":"Dong","sequence":"first","affiliation":[{"name":"University of California,Los Angeles,CA,US,90095"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Utah,Salt Lake City,UT,US,84112"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin F.","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles,CA,US,90095"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Reinforcement learning: An introduction.","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2017.2723574"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2018.7511249"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1007\/BFb0027478","volume-title":"Stability and control of time-delay systems","volume":"228","author":"Dugard","year":"1998"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(03)00167-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09393-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2008.07.007"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref11","first-page":"10746","article-title":"Reinforcement learning in feature space: Matrix bandit, kernels, and regret bound","volume-title":"International Conference on Machine Learning","author":"Yang"},{"article-title":"Is a good representation sufficient for sample efficient reinforcement learning?","volume-title":"International Conference on Learning Representations","author":"Du","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.809799"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9056-7"},{"key":"ref15","first-page":"1453","article-title":"Online learning under delayed feedback","volume-title":"International Conference on Machine Learning","author":"Joulani"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0222-2"},{"key":"ref17","first-page":"33469","article-title":"Near-optimal regret for adversarial mdp with delayed bandit feedback","volume":"35","author":"Jin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Acting in delayed environments with non-stationary markov policies","volume-title":"International Conference on Learning Representations","author":"Derman","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20690"},{"key":"ref20","first-page":"1704","article-title":"Contextual decision processes with low Bellman rank are PAC-learnable","volume-title":"International Conference on Machine Learning","author":"Jiang"},{"key":"ref21","first-page":"2010","article-title":"Sample complexity of reinforcement learning using linearly combined model ensembles","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Modi"},{"key":"ref22","first-page":"10978","article-title":"Learning near optimal policies with low inherent Bellman error","volume-title":"International Conference on Machine Learning","author":"Zanette"},{"key":"ref23","first-page":"6995","article-title":"Sample-optimal parametric Q-learning using linearly additive features","volume-title":"International Conference on Machine Learning","author":"Yang"},{"key":"ref24","first-page":"5662","article-title":"Learning with good feature representations in bandits and in RL with a generative model","volume-title":"International Conference on Machine Learning","author":"Lattimore"},{"article-title":"Provably efficient reinforcement learning for discounted MDPs with feature mapping","volume-title":"International Conference on Machine Learning","author":"Zhou","key":"ref25"},{"key":"ref26","first-page":"2312","article-title":"Improved algorithms for linear stochastic bandits","volume-title":"Proceedings of the 24th International Conference on Neural Information Processing Systems","author":"Abbasi-Yadkori"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_26"},{"key":"ref28","first-page":"1031","article-title":"Model-based reinforcement learning with nearly tight exploration complexity bounds","volume-title":"International Conference on Machine Learning","author":"Szita"},{"issue":"4","key":"ref29","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"Jaksch","year":"2010","journal-title":"Journal of Machine Learning Research"},{"issue":"124","key":"ref30","first-page":"1","article-title":"Deep exploration via randomized value functions","volume":"20","author":"Osband","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","first-page":"2377","article-title":"Generalization and exploration via randomized value functions","volume-title":"International Conference on Machine Learning","author":"Osband"},{"key":"ref32","first-page":"2","article-title":"Bayesian optimal control of smoothly parameterized systems","volume-title":"Uncertainty in Artificial Intelligence: Proceedings of the 31st Conference, UAI 2015","author":"Abbasi-Yadkori"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623497330963"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651374.pdf?arnumber=10651374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:37:17Z","timestamp":1725950237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651374","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}