Ruben Martinez-Cantin Nando de Freitas Arnaud Doucet José A. Castellanos Active Policy Learning for Robot Planning and Exploration under Uncertainty. 2007 Robotics: Science and Systems http://www.roboticsproceedings.org/rss03/p41.html conf/rss/2007 db/conf/rss/rss2007.html#Martinez-CantinFDC07