autonlab.org ____________________ Search * Auton Lab Home * Browse Auton Content * About Us + People + Research Spotlight + Research Thrusts + Jobs * Library + Animations + Papers + Talks + Technical Reports + Tutorials * Downloads + Download Registration + Datasets + Software * Contact + Contact Us * Private Access + Auton Intranet Andrew Ng Papers * Policy Search by Dynamic Programming (2003) Dynamic programming techniques can make direct policy search computationally and sample efficient. * Solving Uncertain Markov Decision Problems (2001) Finding good policies in uncertain models * Applying online search techniques to Continuous-State reinforcement learning (1998) Using a specialized version of A-star to boost the performance of approximate value functions Copyright 2006, Carnegie Mellon University, Auton Lab * User: guest + Login + Change locale * Search * Query Search * Recent Changes * Page Actions + Document Info + Versions + Referrers + Hide navigation * Variants (1) + >> main - en