{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:39:11Z","timestamp":1757630351681,"version":"3.44.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2011,8,1]],"date-time":"2011-08-01T00:00:00Z","timestamp":1312156800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2011,8,1]],"date-time":"2011-08-01T00:00:00Z","timestamp":1312156800000},"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":[[2011,8]]},"DOI":"10.1109\/devlrn.2011.6037356","type":"proceedings-article","created":{"date-parts":[[2011,10,13]],"date-time":"2011-10-13T12:44:03Z","timestamp":1318509843000},"page":"1-8","source":"Crossref","is-referenced-by-count":12,"title":["Artificial curiosity with planning for autonomous perceptual and cognitive development"],"prefix":"10.1109","author":[{"given":"Matthew","family":"Luciw","sequence":"first","affiliation":[{"name":"IDSIA \/ University of Lugano \/ SUPSI \/ 6928 Manno, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Graziano","sequence":"additional","affiliation":[{"name":"IDSIA \/ University of Lugano \/ SUPSI \/ 6928 Manno, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Ring","sequence":"additional","affiliation":[{"name":"IDSIA \/ University of Lugano \/ SUPSI \/ 6928 Manno, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[{"name":"IDSIA \/ University of Lugano \/ SUPSI \/ 6928 Manno, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Reinforcement learning for robots using neural networks","year":"1993","author":"lin","key":"ref10"},{"key":"ref11","article-title":"Stacked convolutional auto-encoders for hierarchical feature extraction","author":"masci","year":"0","journal-title":"International Conference on Artificial Neural Networks"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5732-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"journal-title":"Continual Learning in Reinforcement Environments","year":"1994","author":"ring","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/105971239700600201"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22887-2_3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1990.137723"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"key":"ref19","article-title":"Planning to be surprised: Optimal bayesian exploration in dynamic environments","author":"sun","year":"2011","journal-title":"AGI'II"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22887-2_4"},{"key":"ref3","first-page":"179","article-title":"Adaptive Behaviour in Anticipatory Learning Systems","author":"baldassarre","year":"2003","journal-title":"chapter Forward and bidirectional planning based on reinforcement learning and neural networks in a simulated robot"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23780-5_42"},{"key":"ref5","first-page":"250","article-title":"Reinforcing the driving quality of soccer playing robots by anticipation","volume":"47","author":"gloye","year":"2005","journal-title":"Information technology"},{"key":"ref8","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143901"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/int.20255"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90056-B"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref20","article-title":"First results with DYNA, an integrated architecture for learning, planning and reacting","author":"sutton","year":"0","journal-title":"Proc AAAI Spring Symp Planning Uncertain Unpredictable or Changing Environments"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2007.05.012"},{"key":"ref21","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","author":"sutton","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2009.2021698"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843604000149"}],"event":{"name":"2011 IEEE International Conference on Development and Learning (ICDL)","start":{"date-parts":[[2011,8,24]]},"location":"Frankfurt am Main, Germany","end":{"date-parts":[[2011,8,27]]}},"container-title":["2011 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6031618\/6037311\/06037356.pdf?arnumber=6037356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:42:06Z","timestamp":1757526126000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6037356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,8]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2011.6037356","relation":{},"subject":[],"published":{"date-parts":[[2011,8]]}}}