{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T17:06:23Z","timestamp":1778087183993,"version":"3.51.4"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"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":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tnnls.2021.3119853","type":"journal-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T19:42:25Z","timestamp":1635190945000},"page":"4106-4119","source":"Crossref","is-referenced-by-count":7,"title":["Gradient Monitored Reinforcement Learning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1792-7748","authenticated-orcid":false,"given":"Mohammed Sharafath","family":"Abdul Hameed","sequence":"first","affiliation":[{"name":"Department of Automation Technology, South Westphalia University of Applied Sciences, Soest, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9374-9074","authenticated-orcid":false,"given":"Gavneet Singh","family":"Chadha","sequence":"additional","affiliation":[{"name":"Department of Automation Technology, South Westphalia University of Applied Sciences, Soest, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8405-0977","authenticated-orcid":false,"given":"Andreas","family":"Schwung","sequence":"additional","affiliation":[{"name":"Department of Automation Technology, South Westphalia University of Applied Sciences, Soest, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5149-5918","authenticated-orcid":false,"given":"Steven X.","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Automatic Control and Complex Systems, University of Duisburg-Essen, Duisburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref57","first-page":"244","article-title":"On the optimization of deep networks: Implicit acceleration by overparameterization","volume":"80","author":"arora","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref12","first-page":"2125","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","author":"mohamed","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvfxvcqc.5"},{"key":"ref15","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":"ref59","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref53","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"li","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2834892.2834896"},{"key":"ref11","first-page":"5027","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","author":"conti","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","article-title":"Adapting behaviour for learning progress","author":"schaul","year":"2019","journal-title":"arXiv 1912 06910"},{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref54","first-page":"1","article-title":"Designing neural network architectures using reinforcement learning","author":"baker","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref17","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref19","article-title":"Population based training of neural networks","author":"jaderberg","year":"2017","journal-title":"arXiv 1711 09846"},{"key":"ref18","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref51","first-page":"115","article-title":"Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures","volume":"28","author":"bergstra","year":"2013","journal-title":"Proc 30th Int Conf Int Conf Mach Learn"},{"key":"ref50","first-page":"13956","article-title":"Generalization in reinforcement learning with selective noise injection and information bottleneck","author":"igl","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","first-page":"176","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref45","first-page":"1471","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"greensmith","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref48","article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","author":"justesen","year":"2018","journal-title":"arXiv 1806 10729"},{"key":"ref47","first-page":"1","article-title":"Variance reduction for reinforcement learning in input-driven environments","author":"mao","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref42","first-page":"1","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","author":"lee","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref41","first-page":"598","article-title":"Optimal brain damage","author":"le cun","year":"1990","journal-title":"Advances in neural information processing systems"},{"key":"ref44","first-page":"129","article-title":"What is the state of neural network pruning?","author":"blalock","year":"2020","journal-title":"Proc Mach Learn Syst"},{"key":"ref43","first-page":"1","article-title":"A signal propagation perspective for pruning neural networks at initialization","author":"lee","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref49","first-page":"1","article-title":"Observational overfitting in reinforcement learning","author":"song","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref8","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref7","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":"ref9","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996209"},{"key":"ref5","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"Proc 4th Int Conf Learn Represent"},{"key":"ref40","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"1993","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903070116"},{"key":"ref34","first-page":"1","article-title":"The role of over-parametrization in generalization of neural networks","author":"neyshabur","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","first-page":"822","article-title":"Why do larger models generalize better? A theoretical perspective via the XOR problem","author":"brutzkus","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","author":"kingma","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref33","first-page":"1058","article-title":"Regularization of neural networks using DropConnect","author":"wan","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","article-title":"Learning sparse networks using targeted dropout","author":"gomez","year":"2019","journal-title":"arXiv 1905 13678"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref39","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"1","article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","author":"zhang","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488598000094"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref26","first-page":"540","article-title":"Lessons in neural network training: Overfitting may be harder than expected","author":"lawrence","year":"1997","journal-title":"Proc AAAI\/IAAI"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/34.107014"},{"key":"ref20","first-page":"196","article-title":"Regularizing neural networks with gradient monitoring","author":"chadha","year":"2019","journal-title":"Proc INNS Big Data Deep Learn Conf"},{"key":"ref64","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref21","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref65","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref27","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref29","first-page":"275","article-title":"Deep sparse rectifier neural networks","volume":"15","author":"glorot","year":"2011","journal-title":"Proc AISTATS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/INDIN.2017.8104770"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10208115\/09585302.pdf?arnumber=9585302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:56:18Z","timestamp":1692640578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9585302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":65,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3119853","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}