PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Efficient Reinforcement Learning using Gaussian Processes
Marc Deisenroth
(2010) Karlsruhe Series on Intelligent Sensor Actuator Systems , Volume 9 . KIT Scientific Publishing . ISBN 978-3-86644-569-7

Abstract

This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems. First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model uncertainties consistently into account during long-term planning to reduce model bias. Second, we propose principled algorithms for robust filtering and smoothing in GP dynamic systems.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Book
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:7628
Deposited By:Marc Deisenroth
Deposited On:17 March 2011