{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:01:56Z","timestamp":1781280116209,"version":"3.54.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CAPES - Finance Code 001"},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["310446\/2021-0"],"award-info":[{"award-number":["310446\/2021-0"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["306286\/2020-3"],"award-info":[{"award-number":["306286\/2020-3"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["407063\/2021-8"],"award-info":[{"award-number":["407063\/2021-8"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004901","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","doi-asserted-by":"publisher","award":["3APQ-02228-22"],"award-info":[{"award-number":["3APQ-02228-22"]}],"id":[{"id":"10.13039\/501100004901","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"NVIDIA","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Electron."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tie.2023.3290244","type":"journal-article","created":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T17:15:21Z","timestamp":1688577321000},"page":"6013-6020","source":"Crossref","is-referenced-by-count":39,"title":["Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9653-6050","authenticated-orcid":false,"given":"Victor R. F.","family":"Miranda","sequence":"first","affiliation":[{"name":"Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4940-0377","authenticated-orcid":false,"given":"Armando A.","family":"Neto","sequence":"additional","affiliation":[{"name":"Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5343-7028","authenticated-orcid":false,"given":"Gustavo M.","family":"Freitas","sequence":"additional","affiliation":[{"name":"Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9986-3700","authenticated-orcid":false,"given":"Leonardo A.","family":"Mozelli","sequence":"additional","affiliation":[{"name":"Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref5","first-page":"7968","article-title":"Improving generalization in reinforcement learning with mixture regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2886798"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9217005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103565"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3078390"},{"key":"ref10","first-page":"1","article-title":"An investigation of bug algorithms for mobile robot navigation and obstacle avoidance in two-dimensional unknown static environments","volume-title":"Proc. IEEE Int. Conf. Commun. Inf. Comput. Technol.","author":"Nandesh","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROSE.2011.6058518"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.05.016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9963018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs12111704"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2021.9010012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA48937.2020.9248288"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2019.8832393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00817-z"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341540"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561188"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3078353"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3190850"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3133591"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref26","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref27","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Hu","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-022-10034-z"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"key":"ref30","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/ail2.45"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref33","article-title":"Deep reinforcement learning for real autonomous mobile robot navigation in indoor environments","author":"Surmann","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197159"},{"key":"ref35","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn., ser. Mach. Learn. J. Res. Dy","author":"Fujimoto","year":"2018"},{"key":"ref36","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Lillicrap","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"}],"container-title":["IEEE Transactions on Industrial Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/41\/10416960\/10173760.pdf?arnumber=10173760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T13:54:17Z","timestamp":1706795657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10173760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tie.2023.3290244","relation":{},"ISSN":["0278-0046","1557-9948"],"issn-type":[{"value":"0278-0046","type":"print"},{"value":"1557-9948","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}