{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:26:54Z","timestamp":1784996814329,"version":"3.55.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,6]]},"DOI":"10.1109\/ijcnn.2012.6252823","type":"proceedings-article","created":{"date-parts":[[2012,8,1]],"date-time":"2012-08-01T16:47:51Z","timestamp":1343839671000},"page":"1-8","source":"Crossref","is-referenced-by-count":108,"title":["Autonomous reinforcement learning on raw visual input data in a real world application"],"prefix":"10.1109","author":[{"given":"Sascha","family":"Lange","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Riedmiller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arne","family":"Voigtlander","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651217"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383157"},{"key":"36","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-97966-8","article-title":"Self-organizing maps","volume":"30","author":"kohonen","year":"1997","journal-title":"Springer Series in Information Sciences"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00052"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"15","first-page":"153","article-title":"The difficulty of training deep architectures and the effect of unsupervised pre-training","author":"erhan","year":"2009","journal-title":"Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298623"},{"key":"16","article-title":"Learning a nonlinear embedding by preserving class neighbourhood structure","author":"salakhutdinov","year":"2007","journal-title":"AI and STATISTICS"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273556"},{"key":"37","first-page":"5","article-title":"Effizient klassifizieren und clustern: lernparadigmen von vektorquantisierern","volume":"6","author":"hammer","year":"2006","journal-title":"Knstliche Intelligenz"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553469"},{"key":"38","article-title":"A growing neural gas network learns topologies","volume":"7","author":"fritzke","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"12","first-page":"92","article-title":"Evaluation of pooling operations in convolutional architectures for object recognition","author":"scherer","year":"2010","journal-title":"Proceedings of the 20th International Conference on Artificial Neural Networks Part III Ser icann'Io"},{"key":"21","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","volume":"22","author":"lee","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033458"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"23","first-page":"446","article-title":"Reinforcement learning with raw pixels as input states","author":"ernst","year":"2006","journal-title":"Int Workshop on Intelligent Computing in Pattern Analysis\/Synthesis (IW ICPAS)"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-6226-1"},{"key":"25","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1613\/jair.2110","article-title":"Closed-loop learning of visual control policies","volume":"28","author":"jodogne","year":"2007","journal-title":"Journal of Artificial Intelligence Research"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102401"},{"key":"27","article-title":"Approximate policy iteration for closed-loop learning of visual tasks","author":"lodogne","year":"2006","journal-title":"Proc of the European Conference on Machine Learning"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"29","author":"lange","year":"2010","journal-title":"Tiefes Reinforcement Lemen Auf Basis Visueller Wahrnehmungen"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2009.15"},{"key":"2","article-title":"Adaptive reactive job-shop scheduling with reinforcement learning agents","volume":"24","author":"gabel","year":"2008","journal-title":"International Journal of Information Technology and Intelligent Computing"},{"key":"10","first-page":"539","article-title":"Learning a similarity metric discriminatively, with application to face verification","volume":"1","author":"chopra","year":"2005","journal-title":"Computer Vision and Pattern Recognition 2005 CVPR 2005 IEEE Computer Society Conference on"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"30","article-title":"Deep learning of visual control policies","author":"lange","year":"2010","journal-title":"European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN)"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"6","first-page":"55","article-title":"Reinforcement learning in feedback control","volume":"27","author":"hafner","year":"2011","journal-title":"Machine Learning"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"5","article-title":"Learning to drive in 20 minutes","author":"riedmiller","year":"2007","journal-title":"Proc of the FBlT 2007"},{"key":"31","article-title":"Batch reinforcement learning","author":"lange","year":"2011","journal-title":"Reinforcement Learning State of the Art"},{"key":"4","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"8","first-page":"153","article-title":"Greedy Layer-wise training of deep networks","volume":"19","author":"bengio","year":"2007","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2012 International Joint Conference on Neural Networks (IJCNN 2012 - Brisbane)","location":"Brisbane, Australia","start":{"date-parts":[[2012,6,10]]},"end":{"date-parts":[[2012,6,15]]}},"container-title":["The 2012 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6241467\/6252360\/06252823.pdf?arnumber=6252823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,2]],"date-time":"2019-07-02T07:40:56Z","timestamp":1562053256000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6252823\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2012.6252823","relation":{},"subject":[],"published":{"date-parts":[[2012,6]]}}}