{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:29:25Z","timestamp":1785335365326,"version":"3.55.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordenac\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior\u2014Brasil (CAPES)\u2014Finance Code 001","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006162","name":"Brazilian agencies Funda\u00e7\u00e3o de Amparo a Ci\u00eancia e Tecnologia do Estado de Pernambuco (FACEPE) and Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["432818\/2018-9"],"award-info":[{"award-number":["432818\/2018-9"]}],"id":[{"id":"10.13039\/501100006162","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005853","name":"Universidad Central de Chile","doi-asserted-by":"publisher","award":["CIP2018009"],"award-info":[{"award-number":["CIP2018009"]}],"id":[{"id":"10.13039\/501100005853","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3099071","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T21:48:32Z","timestamp":1627336112000},"page":"104242-104260","source":"Crossref","is-referenced-by-count":21,"title":["A Robust Approach for Continuous Interactive Actor-Critic Algorithms"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5286-3751","authenticated-orcid":false,"given":"Cristian C.","family":"Millan-Arias","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6001-3925","authenticated-orcid":false,"given":"Bruno J. T.","family":"Fernandes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1131-3382","authenticated-orcid":false,"given":"Francisco","family":"Cruz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6199-9685","authenticated-orcid":false,"given":"Richard","family":"Dazeley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5922-4119","authenticated-orcid":false,"given":"Sergio","family":"Fernandes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"ref38","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LA-CCI.2018.8625243"},{"key":"ref32","author":"bellman","year":"2003","journal-title":"Dynamic Programming"},{"key":"ref31","volume":"12","author":"lim","year":"2012","journal-title":"Reinforcement Learning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/9781118266502"},{"key":"ref37","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref34","author":"russell","year":"2003","journal-title":"Artificial Intelligence A Modern Approach"},{"key":"ref60","article-title":"PyRep: Bringing V-REP to deep robot learning","author":"james","year":"2019","journal-title":"arXiv 1906 11176"},{"key":"ref62","first-page":"1","article-title":"A comparison of humanoid robot simulators: A quantitative approach","author":"ayala","year":"2020","journal-title":"Proc Joint IEEE 10th Int Conf Develop Learn Epigenetic Robot (ICDL-EpiRob)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.05.011"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes"},{"key":"ref27","article-title":"Reinforcement learning with human feedback in mountain car","author":"knox","year":"2011","journal-title":"Proc AAAI Spring Symp Help Me Help You Bridging Gaps Hum -Agent Collaboration"},{"key":"ref29","author":"sigaud","year":"2010","journal-title":"Markov Decision Processes in Artificial Intelligence"},{"key":"ref2","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/00223989709603535"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2764499"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0076-5392(08)60497-X"},{"key":"ref23","author":"gross","year":"2005","journal-title":"Psychology The science of mind and behaviour"},{"key":"ref26","first-page":"781","article-title":"Programming robots using reinforcement learning and teaching","author":"lin","year":"1991","journal-title":"Proc 9th Nat Conf Artif Intell (AAAI)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24942-6"},{"key":"ref50","first-page":"278","article-title":"Policy invariance under reward transformations theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"Proc ICML"},{"key":"ref51","article-title":"ICub: Learning emotion expressions using human reward","author":"churamani","year":"2020","journal-title":"arXiv 2003 13483"},{"key":"ref59","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2017.8125811"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/app10165574"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3406499.3418769"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10015-008-0608-3"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICEEE.2018.8533946"},{"key":"ref52","article-title":"A conceptual framework for externally-influenced agents: An assisted reinforcement learning review","author":"bignold","year":"2020","journal-title":"arXiv 2007 01544"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282223"},{"key":"ref11","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"griffith","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref40","article-title":"Online model learning algorithms for ActorCritic control","author":"grondman","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21236\/ADA280844"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(98)00027-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2006.314459"},{"key":"ref18","first-page":"1000","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","author":"thomaz","year":"2006","journal-title":"Proc 21st Nat Conf Artif Intell (AAAI)"},{"key":"ref19","first-page":"661","article-title":"Human feedback in continuous actor-critic reinforcement learning","author":"mill\u00e1n","year":"2019","journal-title":"Proc Eur Symp Artif Neural Netw Comput Intell Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref3","article-title":"On-line Q-learning using connectionist systems","author":"rummery","year":"1994"},{"key":"ref6","first-page":"761","article-title":"Bayesian Q-learning","author":"dearden","year":"1998","journal-title":"Proc 15th AAAI"},{"key":"ref5","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2543839"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2007.4415180"},{"key":"ref49","first-page":"46","article-title":"Between instruction and reward: Human-prompted switching","author":"pilarski","year":"2012","journal-title":"Proc AAAI Fall Symp Robots Learn Interactively Hum Teachers"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3309772.3309801"},{"key":"ref46","article-title":"Human engagement providing evaluative and informative advice for interactive reinforcement learning","author":"bignold","year":"2020","journal-title":"arXiv 2009 09575"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2018.1443318"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329809"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374604"},{"key":"ref44","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":"ref43","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv 1812 05905"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09493212.pdf?arnumber=9493212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:09Z","timestamp":1639771029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9493212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3099071","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}