{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:40:00Z","timestamp":1774964400477,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","award":["W911NF1810334"],"award-info":[{"award-number":["W911NF1810334"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["EPCN 1935389"],"award-info":[{"award-number":["EPCN 1935389"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,25]]},"DOI":"10.23919\/acc50511.2021.9483244","type":"proceedings-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T20:29:16Z","timestamp":1627504156000},"page":"4749-4756","source":"Crossref","is-referenced-by-count":9,"title":["Convex Q-Learning"],"prefix":"10.23919","author":[{"given":"Fan","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prashant G.","family":"Mehta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sean P.","family":"Meyn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gergely","family":"Neu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(85)90317-8"},{"key":"ref38","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref33","article-title":"A unifying view of optimism in episodic reinforcement learning","author":"neu","year":"2020","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref31","article-title":"Playing Atari with deep reinforcement learning","volume":"abs 1312 5602","author":"mnih","year":"2013","journal-title":"ArXiv"},{"key":"ref30","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref36","first-page":"1","article-title":"Stability of stochastic approximations with ‘controlled Markov’ noise and temporal difference learning","author":"ramaswamy","year":"2018","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref35","first-page":"2377","article-title":"Generalization and exploration via randomized value functions","author":"osband","year":"2016","journal-title":"ICML"},{"key":"ref34","article-title":"Deep exploration via randomized value functions","author":"osband","year":"2017","journal-title":"ArXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"ref40","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","article-title":"Accelerating optimization and reinforcement learning with quasi-stochastic approximation","author":"chen","year":"0","journal-title":"To appear ACC 2021"},{"key":"ref12","article-title":"Distributional reinforcement learning with quantile regression","volume":"32","author":"dabney","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.6.850.24925"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1060.0208"},{"key":"ref15","author":"derman","year":"1970","journal-title":"Finite State Markovian Decision Processes volume 67 of Mathematics in Science and Engineering"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_4"},{"key":"ref17","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"ICML"},{"key":"ref18","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref19","article-title":"Rainbow: Combining improvements in deep reinforcement learning","volume":"32","author":"hessel","year":"0","journal-title":"Proceedings of the AAAI"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390240"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029247"},{"key":"ref27","article-title":"Convex Q-learning, part 1: Deterministic optimal control","author":"mehta","year":"2020","journal-title":"ArXiv e-prints"},{"key":"ref3","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"ICML"},{"key":"ref6","author":"bertsekas","year":"2019","journal-title":"REINFORCEMENT LEARNING AND OPTIMAL CONTROL"},{"key":"ref29","author":"meyn","year":"2021","journal-title":"Reinforcement learning and control"},{"key":"ref5","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref8","author":"borkar","year":"2020","journal-title":"Stochastic Approximation A Dynamical Systems Viewpoint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-0805-2_11"},{"key":"ref2","article-title":"Logistic Q-learning","author":"bas-serrano","year":"2021","journal-title":"AISTATS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/18M1229432"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/0331018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2017.2710234"},{"key":"ref45","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815275"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S0168-9274(98)00098-1"},{"key":"ref24","first-page":"719","article-title":"Toward off-policy learning control with function approximation","author":"maei","year":"2010","journal-title":"ICML'10"},{"key":"ref41","article-title":"Deep reinforcement learning with double Q-learning","volume":"30","author":"van hasselt","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref23","article-title":"A unified switching system perspective and ODE analysis of Q-learning algorithms","author":"lee","year":"2019","journal-title":"ArXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2008.10.004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5399753"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/0331024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.6.3.259"}],"event":{"name":"2021 American Control Conference (ACC)","location":"New Orleans, LA, USA","start":{"date-parts":[[2021,5,25]]},"end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9482409\/9482614\/09483244.pdf?arnumber=9483244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T10:50:21Z","timestamp":1633517421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9483244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,25]]},"references-count":45,"URL":"https:\/\/doi.org\/10.23919\/acc50511.2021.9483244","relation":{},"subject":[],"published":{"date-parts":[[2021,5,25]]}}}