Reinforcement learning with Gaussian processes Yaakov Engel Dept. of Computing Science, University of Alberta, Edmonton, Canada Shie Mannor Dept. of Electrical and Computer Engineering, McGill University, Montreal, Cana

First Page		Document Content
Date: 2008-12-01 11:15:01 Control theory Linear filters Stochastic differential equations Kalman filter Markov decision process Normal distribution Gaussian process Q-learning SARSA Statistics Markov models Stochastic processes		Reinforcement learning with Gaussian processes Yaakov Engel Dept. of Computing Science, University of Alberta, Edmonton, Canada Shie Mannor Dept. of Electrical and Computer Engineering, McGill University, Montreal, Cana Document is deleted from original location. Use the Download Button below to download from the Web Archive. Download Document from Web Archive File Size: 262,65 KB

Document is deleted from original location. Use the Download Button below to download from the Web Archive.