{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:09:03Z","timestamp":1729624143483,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1109\/iros.2017.8205962","type":"proceedings-article","created":{"date-parts":[[2017,12,14]],"date-time":"2017-12-14T17:12:59Z","timestamp":1513271579000},"page":"1559-1565","source":"Crossref","is-referenced-by-count":3,"title":["Neural networks for incremental dimensionality reduced reinforcement learning"],"prefix":"10.1109","author":[{"given":"William","family":"Curran","sequence":"first","affiliation":[]},{"given":"Rey","family":"Pocius","sequence":"additional","affiliation":[]},{"given":"William D.","family":"Smart","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1991.139758"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"2319","DOI":"10.1126\/science.290.5500.2319","article-title":"A global geometric framework for nonlinear dimensionality reduction","volume":"290","author":"tenenbaum","year":"2000","journal-title":"Science"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329170"},{"key":"ref30","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"},{"journal-title":"Adaptive Tile Coding for Value Function Approximation","year":"2007","author":"shimon","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2191432"},{"journal-title":"NIPS workshop Reinforcement Learning Benchmarks and Bake-offs II","year":"2005","author":"dutech","key":"ref11"},{"journal-title":"Neural Networks A Comprehensive Foundation","year":"1998","author":"haykin","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"journal-title":"Principal Component Analysis","year":"2002","author":"jolliffe","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1993.716791"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement Learning: A Survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/70.143352"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/robotics2030122"},{"key":"ref19","first-page":"59","article-title":"Directed exploration in reinforcement learning with transferred knowledge","volume":"24","author":"mann","year":"2012","journal-title":"JMLR Workshop and Conference Proceedings"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650243"},{"journal-title":"Introduction to Reinforcement Learning","year":"1998","author":"sutton","key":"ref27"},{"key":"ref3","first-page":"37","article-title":"Autoencoders, unsupervised learning and deep architectures","author":"baldi","year":"2011","journal-title":"Proceedings of the 2011 International Conference on Unsupervised and Transfer Learning Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041454"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363175"},{"key":"ref5","first-page":"213","article-title":"R-MAX - A general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","article-title":"Dimensionality reduced reinforcement learning for assistive robots","author":"curran","year":"2016","journal-title":"Proc of Artificial Intelligence for Human-Robot Interaction at AAAI Fall Symposium Series"},{"journal-title":"Reinforcement learning using neural networks with applications to motor control","year":"2002","author":"coulom","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","first-page":"1281","article-title":"Addressing hard constraints in the air traffic problem through partitioning and difference rewards","author":"curran","year":"2013","journal-title":"Proceedings of the 2013 international conference on Autonomous agents and multiagent systems"},{"key":"ref1","article-title":"Brains, Behavior, and Robotics","author":"sacra albus","year":"1981","journal-title":"BYTE Books"},{"key":"ref20","first-page":"305","article-title":"The kNN-TD reinforcement learning algorithm","author":"antonio","year":"2009","journal-title":"Proceedings of the 3rd International Work-Conference on The Interplay Between Natural and Artificial Computation Part I Methods and Models in Artificial and Natural Computation A Homage to Professor Mira's Scientific Legacy"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45224-9_72"},{"key":"ref21","first-page":"536","article-title":"Kernel pca and denoising in feature spaces","author":"mika","year":"1999","journal-title":"Proceedings of the 1998 conference on Advances in neural information processing systems II"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear dimensionality reduction by locally linear embedding","volume":"290","author":"roweis","year":"2000","journal-title":"Science"},{"key":"ref23","first-page":"278","article-title":"Learning goal-decomposition rules using exercises","author":"reddy","year":"1997","journal-title":"Proceedings of the 14th International Conference on Machine Learning"},{"key":"ref26","first-page":"2413","article-title":"Reinforcement learning in finite MDPs: PAC analysis","volume":"10","author":"strehl","year":"2009","journal-title":"Journal of Machine Learning Research"},{"journal-title":"On the sample complexity of reinforcement learning","year":"2003","author":"kakade","key":"ref25"}],"event":{"name":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2017,9,24]]},"location":"Vancouver, BC","end":{"date-parts":[[2017,9,28]]}},"container-title":["2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8119304\/8202121\/08205962.pdf?arnumber=8205962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,7]],"date-time":"2019-10-07T21:49:47Z","timestamp":1570484987000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8205962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros.2017.8205962","relation":{},"subject":[],"published":{"date-parts":[[2017,9]]}}}