Syndetics cover image
Image from Syndetics

Efficient Reinforcement Learning using Gaussian Processes

By: Contributor(s): Material type: ArticleSeries: Publication details: KIT Scientific Publishing 2010Description: 1 electronic resource (IX, 205 p. p.)Content type:
  • text
Media type:
  • computer
Carrier type:
  • online resource
ISBN:
  • 9783866445697
Subject(s): Online resources: Summary: 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.
No physical items for this record

Open Access Unrestricted online access star

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.

Creative Commons Licence cc by-nc-nd cc https://creativecommons.org/licenses/by-nc-nd/4.0/

eng

Freely available e-book