Efficient reinforcement learning using Gaussian processes

von Marc Peter Deisenroth

205 Seiten, Taschenbuch

Kurzbeschreibung des Verlags

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.

• Reihe: Karlsruhe series on intelligent sensor-actuator-systems
• Themen: Mathematik und Naturwissenschaften Naturwissenschaften, allgemein
• ISBN: 9783866445697
• Sprache: Englisch
• Erscheinungsdatum: 22.11.2010
• Größe: 21 x 14.8 cm
• Verlag: KIT Scientific Publishing