{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T09:43:44Z","timestamp":1773740624605,"version":"3.50.1"},"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":[{"name":"Robots Sociales para Estimulaci\u00f3n F\u00edsica, Cognitiva y Afectiva de Mayores"},{"DOI":"10.13039\/100014440","name":"Innovaci\u00f3n y Universidades and RoboCity2030-DIH-CM through the Ministerio de Ciencia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Madrid Robotics Digital Innovation Hub","award":["S2018\/NMT-4331"],"award-info":[{"award-number":["S2018\/NMT-4331"]}]},{"DOI":"10.13039\/100012818","name":"Programas de Actividades I+D en la Comunidad de Madrid","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012818","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Structural Funds of the European Union"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3095392","type":"journal-article","created":{"date-parts":[[2021,7,7]],"date-time":"2021-07-07T20:09:09Z","timestamp":1625688549000},"page":"98381-98397","source":"Crossref","is-referenced-by-count":12,"title":["Speeding-Up Action Learning in a Social Robot With Dyna-Q+: A Bioinspired Probabilistic Model Approach"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9576-1731","authenticated-orcid":false,"given":"Marcos","family":"Maroto-Gomez","sequence":"first","affiliation":[]},{"given":"Rodrigo","family":"Gonzalez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5189-0002","authenticated-orcid":false,"given":"Alvaro","family":"Castro-Gonzalez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2317-3329","authenticated-orcid":false,"given":"Maria","family":"Malfaz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0263-6606","authenticated-orcid":false,"given":"Miguel Angel","family":"Salichs","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1775","article-title":"Socially-aware reinforcement learning for personalized human-robot interaction","author":"ritschel","year":"2018","journal-title":"Proc 17th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803357"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2017.8172330"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050338"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(96)00068-1"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1109\/TRO.2008.2001362","article-title":"Online affect detection and robot behavior adaptation for intervention of children with autism","volume":"24","author":"liu","year":"2008","journal-title":"IEEE Trans Robot"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301687"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-008-0017-4"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1039-9_2"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.33.2.25"},{"key":"ref61","first-page":"295","article-title":"No bad dogs: Ethological lessons for learning in hamsterdam","author":"blumberg","year":"1996","journal-title":"Proc 4th Int Conf Simulation Adapt Behav From Animals Animats"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2775620"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354145"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2909824.3020217"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593410"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0921-8890(95)00004-Y"},{"key":"ref1","volume":"233","author":"connell","year":"2012","journal-title":"Robot Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2005.1545189"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.1998.724115"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.4017\/gt.2009.08.02.002.00"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3029798.3038362"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-011-0109-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/11840541_57"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat5954"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967936"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956444"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-27645-3_1","article-title":"Reinforcement learning and Markov decision processes","author":"van otterlo","year":"2012","journal-title":"Reinforcement Learning"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3008249"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026004"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2875926"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3055065"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.2018.8604746"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO49542.2019.8961810"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195166194.003.0009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2011.2112766"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3242976"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-020-00687-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2009.5175508"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-011-0113-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/01969722.2014.945321"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"2691","DOI":"10.3390\/s18082691","article-title":"A bio-inspired motivational decision making system for social robots based on the perception of the user","volume":"18","author":"maroto-g\u00f3mez","year":"2018","journal-title":"SENSORS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-013-0225-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/geront\/gny046"},{"key":"ref5","article-title":"Developing social robots for aging populations: A literature review of recent academic sources","volume":"12","author":"pedersen","year":"2018","journal-title":"Comparative Sociology"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5898\/JHRI.1.2.Ferland"},{"key":"ref7","first-page":"66","article-title":"Novel mechanisms for natural human-robot interactions in the DIARC architecture","author":"scheutz","year":"2013","journal-title":"Proc AAAI Workshop Intell Robot Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/267658.267688"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1203"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727679"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.3390\/app11031209","article-title":"Mobile robot path optimization technique based on reinforcement learning algorithm in warehouse environment","volume":"11","author":"lee","year":"2021","journal-title":"Appl Sci"},{"key":"ref47","article-title":"Guided dyna-Q for mobile robot exploration and navigation","author":"hayamizu","year":"2020","journal-title":"arXiv 2004 11456"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2141622.2141690"},{"key":"ref41","first-page":"389","article-title":"Bionic self-learning of two-wheeled robot based on skinner’s operant conditioning","volume":"1","author":"ren","year":"2009","journal-title":"Proc Int Conf Measuring Technol Mechatronics Automat"},{"key":"ref44","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/1729881420921324"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09476021.pdf?arnumber=9476021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T09:21:43Z","timestamp":1643188903000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9476021\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3095392","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}