{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:52:49Z","timestamp":1775868769706,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"PNRR Research Activities of the Consortium Interconnected North-Est Innovation Ecosystem (iNEST) funded by European Union Next-GenerationEU (Piano Nazionale di Ripresa e Resilienza","award":["ECS00000043"],"award-info":[{"award-number":["ECS00000043"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3604290","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:44:37Z","timestamp":1756489477000},"page":"20596-20610","source":"Crossref","is-referenced-by-count":1,"title":["Edge Delayed Deep Deterministic Policy Gradient: Efficient Continuous Control for Edge Scenarios"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0404-6200","authenticated-orcid":false,"given":"Alberto","family":"Sinigaglia","sequence":"first","affiliation":[{"name":"Human Inspired Technology Research Centre, University of Padova, Padua, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2995-4110","authenticated-orcid":false,"given":"Niccol\u00f3","family":"Turcato","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Padova, Padua, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6506-5898","authenticated-orcid":false,"given":"Ruggero","family":"Carli","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Padova, Padua, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-9639","authenticated-orcid":false,"given":"Gian Antonio","family":"Susto","sequence":"additional","affiliation":[{"name":"Human Inspired Technology Research Centre, University of Padova, Padua, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3410162"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3088004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3100709"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3352584"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3530162"},{"key":"ref7","first-page":"8833","article-title":"Reinforcement learning for\n                        athletic intelligence: Lessons from the 1st \u2019AI Olympics with\n                        RealAIGym","volume-title":"Proc. 33rd Int. Joint Conf.\n                        Artif. Intell.","author":"Wiebe"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3398712"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3570620"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3369592"},{"issue":"1","key":"ref11","first-page":"809","article-title":"Policy evaluation with temporal differences: A survey\n                        and comparison","volume":"15","author":"Dann","year":"2014","journal-title":"J. Mach. Learn.\n                        Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref13","article-title":"Continuous control with deep\n                        reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref14","first-page":"1587","article-title":"Addressing function approximation error in\n                        actor-critic methods","volume-title":"Proc. Int. Conf.\n                        Mach. Learn.","author":"Fujimoto"},{"key":"ref15","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep\n                        reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3440047"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3556875"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3357204"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3264237"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.1081242"},{"key":"ref23","first-page":"1","article-title":"Randomized ensembled double Q-learning: Learning fast\n                        without a model","volume-title":"Proc. Int. Conf. Learn.\n                        Represent.","author":"Chen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107286"},{"key":"ref25","article-title":"S2AC: Energy-based\n                        reinforcement learning with stein soft actor critic","author":"Messaoud","year":"2024","journal-title":"arXiv:2405.00987"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICARA64554.2025.10977694"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3043716"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2015.2417684"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3469116.3470015"},{"key":"ref30","article-title":"A survey on deep neural network pruning-taxonomy,\n                        comparison, analysis, and recommendations","author":"Cheng","year":"2023","journal-title":"arXiv:2308.06767"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref32","article-title":"OpenAI\n                    gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3117949"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3036808"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3312237"},{"key":"ref36","first-page":"255","article-title":"Issues in using function approximation for\n                        reinforcement learning","volume-title":"Proc.\n                        Connectionist Models Summer School","author":"Thrun"},{"key":"ref37","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Hasselt"},{"key":"ref38","first-page":"1","article-title":"Maxmin Q-learning: Controlling the estimation bias of\n                        Q-learning","volume-title":"Proc. Int. Conf. Learn.\n                        Represent.","author":"Lan"},{"key":"ref39","first-page":"5556","article-title":"Controlling overestimation bias with truncated\n                        mixture of continuous distributional quantile\n                    critics","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Kuznetsov"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20840"},{"key":"ref41","first-page":"1","article-title":"When to trust your model: Model-based policy\n                        optimization","volume-title":"Proc. Adv. Neural Inf.\n                        Process. Syst.","author":"J\u00e4nner"},{"key":"ref42","first-page":"387","article-title":"Deterministic policy gradient\n                        algorithms","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Silver"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2307\/1911031"},{"key":"ref44","article-title":"Adam: A method for stochastic\n                        optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref45","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1028144858"},{"key":"ref47","article-title":"An overview of gradient descent optimization\n                        algorithms","author":"Ruder","year":"2016","journal-title":"arXiv:1609.04747"},{"key":"ref48","article-title":"Explaining and harnessing adversarial\n                        examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref49","first-page":"3692","article-title":"Smoothed action value functions for learning Gaussian\n                        policies","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Nachum"},{"key":"ref50","article-title":"Spectral normalization for generative adversarial\n                        networks","author":"Miyato","year":"2018","journal-title":"arXiv:1802.05957"},{"key":"ref51","first-page":"833","article-title":"Contractive auto-encoders: Explicit invariance during\n                        feature extraction","volume-title":"Proc. 28th Int. Conf.\n                        Mach. Learn. (ICML)","author":"Rifai"},{"key":"ref52","article-title":"How to train your energy-based\n                    models","author":"Song","year":"2021","journal-title":"arXiv:2101.03288"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-020-00896-5"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2984887"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref56","article-title":"Proximal policy optimization\n                        algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11145085.pdf?arnumber=11145085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T05:16:12Z","timestamp":1774329372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11145085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3604290","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}