{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:31:30Z","timestamp":1730341890274,"version":"3.28.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"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":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867291","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:10Z","timestamp":1662409450000},"page":"3317-3322","source":"Crossref","is-referenced-by-count":1,"title":["Convex Programs and Lyapunov Functions for Reinforcement Learning: A Unified Perspective on the Analysis of Value-Based Methods"],"prefix":"10.23919","author":[{"given":"Xingang","family":"Guo","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Coordinated Science Laboratory (CSL),Department of Electrical and Computer Engineering"}]},{"given":"Bin","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Coordinated Science Laboratory (CSL),Department of Electrical and Computer Engineering"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6161293"},{"journal-title":"Positive Linear Systems Theory and Applications","year":"2011","author":"farina","key":"ref38"},{"key":"ref33","article-title":"Two time-scale off-policy TD learning: Non-asymptotic analysis over Markovian samples","author":"xu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref32","first-page":"2803","article-title":"Finite-time error bounds for linear stochastic approximation and TD learning","author":"srikant","year":"2019","journal-title":"Conference on Learning Theory"},{"key":"ref31","first-page":"1691","article-title":"A finite time analysis of temporal difference learning with linear function approximation","author":"bhandari","year":"2018","journal-title":"Conference on Learning Theory"},{"key":"ref30","volume":"5","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/20M1322649"},{"key":"ref36","article-title":"Finite sample analysis of average-reward TD learning and Q-learning","volume":"34","author":"zhang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref35","first-page":"10 555","article-title":"A finite-time analysis of Q-learning with neural network function approximation","author":"xu","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref34","first-page":"4485","article-title":"Finite-time analysis of decentralized temporal-difference learning with linear function approximation","author":"sun","year":"2020","journal-title":"AISTATS"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref28"},{"key":"ref27","first-page":"3143","article-title":"PID accelerated value iteration algorithm","author":"farahmand","year":"2021","journal-title":"International Conference on Machine Learning"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref29"},{"key":"ref2","first-page":"343","article-title":"A general analysis of the convergence of ADMM","author":"nishihara","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/15M1009597"},{"key":"ref20","first-page":"8525","article-title":"A universally optimal multistage accelerated stochastic gradient method","author":"aybat","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2020.2988009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2020.1745286"},{"key":"ref24","first-page":"15 556","article-title":"A unified switching system perspective and convergence analysis of Q-learning algorithms","volume":"33","author":"lee","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"8479","article-title":"Characterizing the exact behaviors of temporal difference learning algorithms using Markov jump linear system theory","author":"hu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"ref25","volume":"48","author":"borkar","year":"2009","journal-title":"Stochastic Approximation A Dynamical Systems Viewpoint"},{"key":"ref50","first-page":"247","article-title":"Stability and control of discrete-time jump linear systems","volume":"7","author":"ji","year":"1991","journal-title":"Control-Theory and Advanced Technology"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.817010"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/5.871309"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2019.2920342"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/19M1244925"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1561\/2600000005"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2019.108715","article-title":"Analytical convergence regions of accelerated gradient descent in nonconvex optimization under regularity condition","volume":"113","author":"xiong","year":"2020","journal-title":"Automatica"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3008297"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01486-1"},{"key":"ref15","first-page":"1","article-title":"A frequency-domain analysis of inexact gradient methods","author":"gannot","year":"2021","journal-title":"Mathematical Programming"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2017.2722406"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430824"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8618984"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431231"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/17M1136845"},{"key":"ref3","first-page":"1549","article-title":"Dissipativity theory for Nesterov&#x2019;s accelerated method","volume":"70","author":"hu","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262874"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2823264"},{"key":"ref7","first-page":"1157","article-title":"A unified analysis of stochastic optimization methods using jump system theory and quadratic constraints","volume":"65","author":"hu","year":"2017","journal-title":"Conference on Learning Theory"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2002.800674"},{"key":"ref9","first-page":"2043","article-title":"Dissipativity theory for accelerating stochastic variance reduction: A unified analysis of SVRG and Katyusha using semidefinite programs","author":"hu","year":"2018","journal-title":"International Conference on Machine Learning"},{"journal-title":"Discrete-Time Markov Jump Linear Systems","year":"2006","author":"costa","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.043"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1239(199611)6:9\/10<1015::AID-RNC266>3.0.CO;2-0"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1006\/jmaa.1993.1341"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.900857"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1109\/TCSII.2009.2019326","article-title":"Stability analysis of switched positive systems: a switched linear copositive Lyapunov function method","volume":"56","author":"liu","year":"2009","journal-title":"IEEE Trans on Circuits and Systems II Express Briefs"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2173416"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.04.037"}],"event":{"name":"2022 American Control Conference (ACC)","start":{"date-parts":[[2022,6,8]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867291.pdf?arnumber=9867291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T20:38:09Z","timestamp":1664829489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":52,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867291","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}