Efficient reinforcement learning using Gaussian processes

Beschreibung

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.
Printing on Demand. Kostenloser Download über den Verlagsserver unter der URL http://www.ksp.kit.edu/shop/isbn/978-3-86644-569-7

Autor*in

Marc Peter Deisenroth

Themen in »Efficient reinforcement learning using Gaussian processes«

control machine learning autonomous learning Gaussian processes Bayesian inference

Stimmen zu »Efficient reinforcement learning using Gaussian processes«

Details

Link teilen