{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T15:06:27Z","timestamp":1730214387236,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/devlrn.2018.8761021","type":"proceedings-article","created":{"date-parts":[[2019,7,15]],"date-time":"2019-07-15T20:17:08Z","timestamp":1563221828000},"page":"33-38","source":"Crossref","is-referenced-by-count":2,"title":["Developmental Reinforcement Learning through Sensorimotor Space Enlargement"],"prefix":"10.1109","author":[{"given":"Matthieu","family":"Zimmer","sequence":"first","affiliation":[]},{"given":"Yann","family":"Boniface","sequence":"additional","affiliation":[]},{"given":"Alain","family":"Dutech","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Progressive Neural Networks","author":"rusu","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref32","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning?","volume":"11","author":"erhan","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","article-title":"Bootstrapping Q-Learning for Robotics from Neuro-Evolution Results","author":"zimmer","year":"2017","journal-title":"IEEE Transactions on Cognitive and Developmental System"},{"key":"ref30","first-page":"1","article-title":"Adam: a Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref34","article-title":"Pathnet: Evolution channels gradient descent in super neural networks","author":"fernando","year":"2017","journal-title":"ArXiv Preprint"},{"journal-title":"Open dynamics engine","year":"2005","author":"smith","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref12","first-page":"1607","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"Association for the Advancement of Artificial Intelligence"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref15","first-page":"1008","article-title":"Actor-Critic Algorithms","volume":"13","author":"konda","year":"1999","journal-title":"Neural Information Processing Systems"},{"key":"ref16","article-title":"Deep Reinforcement Learning that Matters","author":"henderson","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"},{"key":"ref19","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","author":"ioffe","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"698","article-title":"Learning to control a 6-degree-of-freedom walking robot","author":"wawrzy?ski","year":"2007","journal-title":"International Conference on Computer as a Tool"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref27","first-page":"93","article-title":"How can we define intrinsic motivation?","author":"oudeyer","year":"0","journal-title":"8th Int Conf Epigenetic Robotics"},{"key":"ref3","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2009.2021702"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref5","first-page":"1633","article-title":"Transfer Learning for Reinforcement Learning Domains: A Survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888911000038"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref9"},{"journal-title":"Reinforcement Learning An Introduction (Adaptive Computation and Machine Learning)","year":"1998","author":"sutton","key":"ref1"},{"key":"ref20","article-title":"Neural Fitted Actor-Critic","author":"zimmer","year":"2016","journal-title":"European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref24","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"},{"journal-title":"Developmental reinforcement learning","year":"2018","author":"zimmer","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"}],"event":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","start":{"date-parts":[[2018,9,17]]},"location":"Tokyo, Japan","end":{"date-parts":[[2018,9,20]]}},"container-title":["2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8753819\/8760502\/08761021.pdf?arnumber=8761021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T20:59:10Z","timestamp":1565643550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8761021\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2018.8761021","relation":{},"subject":[],"published":{"date-parts":[[2018,9]]}}}