{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:37:01Z","timestamp":1773329821241,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2015,7,1]],"date-time":"2015-07-01T00:00:00Z","timestamp":1435708800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2015,7,1]],"date-time":"2015-07-01T00:00:00Z","timestamp":1435708800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,7]]},"DOI":"10.1109\/ijcnn.2015.7280477","type":"proceedings-article","created":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T17:48:02Z","timestamp":1443721682000},"page":"1-8","source":"Crossref","is-referenced-by-count":37,"title":["Interactive reinforcement learning through speech guidance in a domestic scenario"],"prefix":"10.1109","author":[{"given":"Francisco","family":"Cruz","sequence":"first","affiliation":[{"name":"Knowledge Technology Group, Department of Informatics, University of Hamburg, Vogt-Kölln-Str. 30, 22527, Germany"}]},{"given":"Johannes","family":"Twiefel","sequence":"additional","affiliation":[{"name":"Knowledge Technology Group, Department of Informatics, University of Hamburg, Vogt-Kölln-Str. 30, 22527, Germany"}]},{"given":"Sven","family":"Magg","sequence":"additional","affiliation":[{"name":"Knowledge Technology Group, Department of Informatics, University of Hamburg, Vogt-Kölln-Str. 30, 22527, Germany"}]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[{"name":"Knowledge Technology Group, Department of Informatics, University of Hamburg, Vogt-Kölln-Str. 30, 22527, Germany"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[{"name":"Knowledge Technology Group, Department of Informatics, University of Hamburg, Vogt-Kölln-Str. 30, 22527, Germany"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Machine learning: a probabilistic perspective","author":"murphy","year":"2012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref33","article-title":"On-Line Q-Learning using Connectionist Systems","author":"rummery","year":"1994","journal-title":"Cambridge University Engineering Department"},{"key":"ref32","article-title":"From Affordances to Situated Affordances in Robotics - Why Context is Important","volume":"5","author":"kammer","year":"2011","journal-title":"Frontiers in Computational Neuroscience (Conference Abstract IEEE ICDL-EPIROB 2011)"},{"key":"ref31","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions and reversals","volume":"10","author":"levenshtein","year":"1966","journal-title":"Soviet Physics Doklady"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.01.002"},{"key":"ref37","first-page":"18","article-title":"On the expressive power of deep architectures","volume":"6925","author":"bengio","year":"2011"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multi-layer feedforward networks are universal approximators","volume":"2","author":"hornik","year":"1989","journal-title":"Neural Networks"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90003-8"},{"key":"ref34","first-page":"303","article-title":"Approximaiion by superpositions of a sigmoid function","volume":"2","author":"cybenko","year":"1989"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0163-x"},{"key":"ref40","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref12","first-page":"781","article-title":"Programming Robots Using Reinforcement Learning and Teaching","author":"lin","year":"1991","journal-title":"AAAI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843612500065"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911428653"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-012-0128-9"},{"key":"ref16","first-page":"627","article-title":"Towards Robot Skill Learning: From Simple Skills to Table Tennis","volume":"8190","author":"peters","year":"2013","journal-title":"Machine Learning and Knowledge Discovery in Databases"},{"key":"ref17","first-page":"1000","article-title":"Reinforcement learning with human teachers: evidence of feedback and guidance with implications for learning performance","volume":"1","author":"thomaz","year":"2006","journal-title":"Proceedings of the 21st National Conference on Artificial Intelligence"},{"key":"ref18","article-title":"Real-Time Interactive Reinforcement Learning for Robots","author":"thomaz","year":"2005","journal-title":"Proceedings of AAAI Workshop on Human Comprehensible Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2451176.2451201"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-5951-5_4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref27","first-page":"149","article-title":"Affordances and Emergence of Concepts","author":"atil","year":"2010","journal-title":"Proceedings of 10th International Conference on Epigenetic Robotics Modeling Cognitive Development in Robotic Systems"},{"key":"ref3","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","author":"gibson","year":"1986","journal-title":"The Ecological Approach to Visual Perception"},{"key":"ref29","first-page":"1529","article-title":"Improving Domain-independent Cloud-based Speech Recognition with Domain-dependent Phonetic Post-processing","author":"twiefel","year":"2014","journal-title":"Proceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI-14)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_18"},{"key":"ref8","first-page":"720","article-title":"Asymmetric Interpretations of Positive and Negative Human Feedbackfor a Social Learning Agent","author":"thomaz","year":"2007","journal-title":"Proc IEEE RO-MAN 2007"},{"key":"ref7","first-page":"70","article-title":"Affordances for robots: a brief survey","author":"horton","year":"2012","journal-title":"AVANT Journal of Philosophical-Interdisciplinary Vanguard"},{"key":"ref2","author":"bishop","year":"2011","journal-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2014.2310151"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2012.6343862"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2014.6982975"},{"key":"ref21","first-page":"2625","article-title":"Policy Shaping: Integrating Human Feedback With Reinforcement Learning","author":"griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/72.329697"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/1059712307084689"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1990.137819"},{"key":"ref23","article-title":"Radical embodied cognitive science","author":"chemero","year":"2011"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2007.914848"},{"key":"ref43","first-page":"142","article-title":"Interaction is more beneficial in complex reinforcement learning problems than in simple ones","author":"stahlhut","year":"2015","journal-title":"Proceedings of the Interdisziplinarer Workshop Kognitive Systeme (KogSys)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/1059712307085098"}],"event":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","location":"Killarney, Ireland","start":{"date-parts":[[2015,7,12]]},"end":{"date-parts":[[2015,7,17]]}},"container-title":["2015 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7256526\/7280295\/07280477.pdf?arnumber=7280477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:26:57Z","timestamp":1755908817000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7280477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2015.7280477","relation":{},"subject":[],"published":{"date-parts":[[2015,7]]}}}