{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T04:06:45Z","timestamp":1751602005767,"version":"3.41.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1109\/devlrn.2017.8329828","type":"proceedings-article","created":{"date-parts":[[2018,4,6]],"date-time":"2018-04-06T04:26:54Z","timestamp":1522988814000},"page":"344-349","source":"Crossref","is-referenced-by-count":1,"title":["A deep reinforcement learning based model supporting object familiarization"],"prefix":"10.1109","author":[{"given":"Maximilian","family":"Panzner","sequence":"first","affiliation":[]},{"given":"Philipp","family":"Cimiano","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1","article-title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","author":"clevert","year":"2015","journal-title":"Under Rev ICLR2016"},{"key":"ref11","first-page":"1","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"},{"key":"ref12","first-page":"1","article-title":"Adam: a Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"Proceedings of the 2015 International Conference on Learning Representations"},{"key":"ref13","first-page":"2","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref14","first-page":"2121","article-title":"Adaptive Subgradient Methods for Online Learning and Stochastic Optimization","volume":"12","author":"duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","volume":"2","author":"sutton","year":"2017","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref16","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","volume":"17","author":"singh","year":"2004","journal-title":"The Annual Conference on Neural Information Processing System (NIPS)"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"222","DOI":"10.7551\/mitpress\/3115.003.0030","article-title":"A Possibility for Implementing Curiosity and Boredom in Model-Building Neural Controllers","volume":"1","author":"schmidhuber","year":"1991","journal-title":"From Animals to Animats"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref6","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"CoRR"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref7","first-page":"1","author":"van hasselt","year":"2015","journal-title":"Deep reinforcement learning with double q-learning"},{"journal-title":"Deep familiarization and learning grounded in cooperative manual action and language","year":"0","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s002210050550"},{"key":"ref9","first-page":"2613","article-title":"Double q-learning","author":"van hasselt","year":"2010","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","start":{"date-parts":[[2017,9,18]]},"location":"Lisbon","end":{"date-parts":[[2017,9,21]]}},"container-title":["2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8326423\/8329770\/08329828.pdf?arnumber=8329828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T13:21:34Z","timestamp":1751548894000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8329828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2017.8329828","relation":{},"subject":[],"published":{"date-parts":[[2017,9]]}}}