{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T22:34:59Z","timestamp":1779402899034,"version":"3.53.1"},"reference-count":152,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61673179"],"award-info":[{"award-number":["61673179"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Sailing Program","award":["17YF1404600"],"award-info":[{"award-number":["17YF1404600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/tcyb.2019.2950779","type":"journal-article","created":{"date-parts":[[2019,11,19]],"date-time":"2019-11-19T20:55:18Z","timestamp":1574196918000},"page":"3668-3681","source":"Crossref","is-referenced-by-count":632,"title":["A Survey of Optimization Methods From a Machine Learning Perspective"],"prefix":"10.1109","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7069-3752","authenticated-orcid":false,"given":"Shiliang","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehui","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0158-5330","authenticated-orcid":false,"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref38","first-page":"1","article-title":"Improving generalization performance by switching from Adam to SGD","author":"keskar","year":"2017","journal-title":"arXiv preprint arXiv 1712 07628"},{"key":"ref33","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref32","first-page":"26","article-title":"Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref31","first-page":"1","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv preprint arXiv 1212 5701"},{"key":"ref30","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref37","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","author":"johnson","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"2663","article-title":"A stochastic gradient method with an exponential convergence rate for finite training sets","author":"roux","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","first-page":"1","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"arXiv preprint arXiv 1511 06434"},{"key":"ref34","first-page":"1","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2814824"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441697"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927639"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref21","first-page":"2873","article-title":"Recurrent neural network for text classification with multi-task learning","author":"liu","year":"2016","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref24","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"oord","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"1462","article-title":"DRAW: A recurrent neural network for image generation","author":"gregor","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2500618"},{"key":"ref100","first-page":"797","article-title":"Escaping from saddle points—Online stochastic gradient for tensor decomposition","author":"ge","year":"2015","journal-title":"Proc Conf Learn Theory"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2778011"},{"key":"ref50","first-page":"1","article-title":"Siamese neural networks for one-shot image recognition","author":"koch","year":"2015","journal-title":"Proc Int Machine Learning Workshop"},{"key":"ref51","first-page":"3630","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1137\/140954362"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2868835"},{"key":"ref151","first-page":"1737","article-title":"SGD-QN: Careful quasi-Newton stochastic gradient descent","volume":"10","author":"bordes","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref146","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst Workshop"},{"key":"ref147","author":"martens","year":"2016","journal-title":"Second-Order Optimization For Neural Networks"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46084-5_218"},{"key":"ref149","first-page":"436","article-title":"A stochastic quasi-Newton method for online convex optimization","author":"schraudolph","year":"2007","journal-title":"Proc Artif Intell Stat"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref58","first-page":"1303","article-title":"Stochastic variational inference","volume":"14","author":"hoffman","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref57","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref56","first-page":"1","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref55","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","first-page":"1","article-title":"Memory networks","author":"weston","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref53","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","author":"santoro","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34500-5_16"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/18M121112X"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1970-0274029-X"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/1019005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05807-0"},{"key":"ref8","first-page":"1","article-title":"Sub-sampled Newton methods II: Local convergence rates","author":"roosta-khorasani","year":"2016","journal-title":"arXiv preprint arXiv 1601 04738"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1142\/9789812797926_0003"},{"key":"ref7","first-page":"735","article-title":"Deep learning via Hessian-free optimization","author":"martens","year":"2010","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","first-page":"3000","article-title":"Sub-sampled Newton methods with non-uniform sampling","author":"xu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.4650"},{"key":"ref45","article-title":"Evolutionary principles in self-referential learning, or on learning how to learn: The meta-meta-$\\ldots$\n hook","author":"schmidhuber","year":"1987"},{"key":"ref48","author":"vinyals","year":"2017","journal-title":"Model vs Optimization Meta Learning"},{"key":"ref47","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref41","first-page":"1","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst Workshop"},{"key":"ref44","first-page":"426","article-title":"Deep reinforcement learning: An overview","author":"mousavi","year":"2016","journal-title":"Proc SAI Intell Syst Conf"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2014.04.013"},{"key":"ref126","author":"andersen","year":"2013","journal-title":"Cvxopt A Python Package for Convex Optimization Version 1 1 6"},{"key":"ref125","first-page":"2909","article-title":"CVXPY: A python-embedded modeling language for convex optimization","volume":"17","author":"diamond","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref124","author":"grant","year":"2014","journal-title":"CVX Matlab Software for Disciplined Convex Programming Version 2 1"},{"key":"ref73","first-page":"809","article-title":"Semi-supervised clustering using genetic algorithms","volume":"1","author":"demiriz","year":"1999","journal-title":"Artificial Neural Networks in Engineering"},{"key":"ref72","first-page":"908","article-title":"Semi-supervised regression with co-training","author":"zhou","year":"2005","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref129","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX Symp on Operating System Design and Implementation"},{"key":"ref71","first-page":"57","article-title":"Semi-supervised classification by low density separation","author":"chapelle","year":"2005","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref128","author":"mairal","year":"2014","journal-title":"SPAMS Sparse modeling software version 2 0"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540120"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.08.010"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"ref77","first-page":"368","article-title":"Semi-supervised support vector machines","author":"bennett","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5084-4"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972771.73"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1561\/2200000058"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1016\/S0098-1354(98)00027-1"},{"key":"ref131","first-page":"1","article-title":"Recurrent neural network regularization","author":"zaremba","year":"2015","journal-title":"arXiv preprint arXiv 1409 2329"},{"key":"ref78","author":"cheung","year":"2018","journal-title":"Optimization Methods for Semi-Supervised Learning"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref79","first-page":"203","article-title":"Optimization techniques for semi-supervised support vector machines","volume":"9","author":"chapelle","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206604"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-0303-9_1"},{"key":"ref138","first-page":"1","article-title":"Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees","author":"chen","year":"2015","journal-title":"arXiv preprint arXiv 1509 03025"},{"key":"ref137","first-page":"904","article-title":"Unsupervised and semi-supervised multi-class support vector machines","author":"xu","year":"2005","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref60","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref139","first-page":"1","article-title":"Provable non-convex projected gradient descent for a class of constrained matrix optimization problems","author":"park","year":"2016","journal-title":"arXiv preprint arXiv 1606 01316"},{"key":"ref62","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref61","first-page":"1683","article-title":"Stochastic gradient Hamiltonian Monte Carlo","author":"chen","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K15-1021"},{"key":"ref64","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"yang","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1145\/2488608.2488693"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2009.2023983"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.75"},{"key":"ref66","first-page":"3642","article-title":"Multi-column deep neural networks for image classification","author":"ciresan","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref142","first-page":"638","article-title":"Fast matrix completion without the condition number","author":"hardt","year":"2014","journal-title":"Proc Conf Learn Theory"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1214\/16-AOS1435"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4379(00)00022-3"},{"key":"ref144","first-page":"1","article-title":"High dimensional expectation maximization algorithm: Statistical optimization and asymptotic normality","author":"wang","year":"2014","journal-title":"arXiv preprint arXiv 1412 8729"},{"key":"ref2","first-page":"1","article-title":"Parallelizing stochastic gradient descent for least squares regression: Mini-batching, averaging, and model misspecification","volume":"18","author":"jain","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.2172\/807420"},{"key":"ref145","first-page":"1","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref109","first-page":"314","article-title":"Stochastic variance reduction for nonconvex optimization","author":"reddi","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref108","first-page":"699","article-title":"Variance reduction for faster non-convex optimization","author":"allen-zhu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref94","author":"nemirovsky","year":"1983","journal-title":"Problem Complexity and Method Efficiency in Optimization"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1030-6"},{"key":"ref93","author":"nocedal","year":"2006","journal-title":"Numerical Optimization"},{"key":"ref106","first-page":"832","article-title":"Note on learning rate schedules for stochastic optimization","author":"darken","year":"1991","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref92","first-page":"836","article-title":"A parallel gradient descent method for learning in analog VLSI neural networks","author":"alspector","year":"1993","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref105","first-page":"968","article-title":"Gradient descent for general reinforcement learning","author":"baird","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref104","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the rate of convergence $O\\left({\\frac{1}{k^{2}}}\\right)$","volume":"269","author":"nesterov","year":"1983","journal-title":"Doklady Akademii Nauk SSSR"},{"key":"ref90","first-page":"1","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref103","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref102","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref111","first-page":"283","article-title":"A method for nonlinear constraints in minimization problems","author":"powell","year":"1969","journal-title":"Optimization"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref110","first-page":"1646","article-title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","author":"defazio","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref98","article-title":"Training recurrent neural networks","author":"sutskever","year":"2013"},{"key":"ref99","first-page":"2675","article-title":"Natasha 2: Faster non-convex optimization than SGD","author":"allen-zhu","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref96","first-page":"1","article-title":"Information-theoretic lower bounds on the oracle complexity of convex optimization","author":"agarwal","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/NNSP.1992.253713"},{"key":"ref10","first-page":"1","article-title":"Exact and inexact subsampled Newton methods for optimization","volume":"1","author":"bollapragada","year":"2018","journal-title":"IMA J Numer Anal"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-012-9951-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/18M1177718"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref14","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"1","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref118","first-page":"427","article-title":"Revisiting Frank–Wolfe: Projection-free sparse convex optimization","author":"jaggi","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/26.4.354"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800030109"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref81","first-page":"2151","article-title":"Convex and scalable weakly labeled SVMs","volume":"14","author":"li","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1002\/bs.3830120210"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/0191-2615(84)90029-8"},{"key":"ref19","first-page":"2267","article-title":"Recurrent convolutional neural networks for text classification","author":"lai","year":"2015","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44533-1_24"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1023\/A:1004603514434"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.30.1.3"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.3182\/20120711-3-BE-2027.00310"},{"key":"ref80","first-page":"217","article-title":"Branch and bound for semi-supervised support vector machines","author":"chapelle","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref115","first-page":"1","article-title":"SnapVX: A network-based convex optimization solver","volume":"18","author":"hallac","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref120","author":"patriksson","year":"2015","journal-title":"The Traffic Assignment Problem Models and Methods"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/1824777.1824783"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/S0168-9274(98)00117-2"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.2002.7176"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_455"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00196"},{"key":"ref88","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9138538\/08903465.pdf?arnumber=8903465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:20:48Z","timestamp":1651080048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8903465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":152,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2019.2950779","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8]]}}}