{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T22:09:05Z","timestamp":1773698945626,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Contr. Syst. Technol."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcst.2024.3393210","type":"journal-article","created":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T18:16:38Z","timestamp":1715969798000},"page":"2102-2113","source":"Crossref","is-referenced-by-count":11,"title":["Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2997-543X","authenticated-orcid":false,"given":"Francesco","family":"De Lellis","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2784-1486","authenticated-orcid":false,"given":"Marco","family":"Coraggio","sequence":"additional","affiliation":[{"name":"School for Advanced Studies, Scuola Superiore Meridionale, Naples, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5001-3027","authenticated-orcid":false,"given":"Giovanni","family":"Russo","sequence":"additional","affiliation":[{"name":"Department of Computer and Electrical Engineering and Applied Mathematics, DIEM, University of Salerno, Salerno, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9712-4090","authenticated-orcid":false,"given":"Mirco","family":"Musolesi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2171-4745","authenticated-orcid":false,"given":"Mario","family":"di Bernardo","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2020.3007401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2022.3223185"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.619"},{"key":"ref7","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","volume-title":"Proc. 15th Int. Conf. Mach. Learn.","author":"Randl\u00f8v"},{"key":"ref8","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref9","first-page":"15281","article-title":"Unpacking reward shaping: Understanding the benefits of reward engineering on sample complexity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Gupta"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.008"},{"issue":"4","key":"ref11","first-page":"803","article-title":"Lyapunov design for safe reinforcement learning","volume":"3","author":"Perkins","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","first-page":"1","article-title":"Safe model-based reinforcement learning with stability guarantees","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berkenkamp"},{"key":"ref13","first-page":"1","article-title":"A Lyapunov-based approach to safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chow"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2020.03.001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1115\/1.3653115"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/37.506395"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992796"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383391"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3079642"},{"key":"ref22","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref23","volume-title":"OpenAI Gym Pendulum Online Documentation","year":"2022"},{"key":"ref24","volume-title":"OpenAI Gym Lunar Lander Online Documentation","year":"2022"},{"key":"ref25","volume-title":"Reward Shaping for RL Based Control","author":"De Lellis","year":"2023"},{"key":"ref26","first-page":"941","article-title":"CT-DQN: Control-tutored deep reinforcement learning","volume-title":"Proc. 5th Annu. Learn. Dyn. Control Conf.","volume":"211","author":"De Lellis"},{"key":"ref27","first-page":"1048","article-title":"Control-tutored reinforcement learning: Towards the integration of data-driven and model-based control","volume-title":"Proc. 4th Annu. Learn. Dyn. Control Conf.","volume":"168","author":"De Lellis"},{"key":"ref28","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Riedmiller"},{"key":"ref29","first-page":"1","article-title":"Reinforcement learning with sparse rewards using guidance from offline demonstration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rengarajan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1515\/9781400828739"},{"key":"ref31","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636020"}],"container-title":["IEEE Transactions on Control Systems Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/87\/10736368\/10534075.pdf?arnumber=10534075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:19:59Z","timestamp":1732666799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10534075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":35,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcst.2024.3393210","relation":{},"ISSN":["1063-6536","1558-0865","2374-0159"],"issn-type":[{"value":"1063-6536","type":"print"},{"value":"1558-0865","type":"electronic"},{"value":"2374-0159","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}