*Result*: Efficient Reinforcement Learning using Gaussian Processes
Title:
Efficient Reinforcement Learning using Gaussian Processes
Authors:
Publisher Information:
KIT Scientific Publishing
Publication Year:
2021
Collection:
Directory of Open Access Books (DOAB)
Subject Terms:
Document Type:
other/unknown material
File Description:
image/jpeg
Language:
English
ISBN:
978-3-86644-569-7
3-86644-569-5
3-86644-569-5
ISSN:
18673813
Relation:
Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory; 35389; https://www.ksp.kit.edu/9783866445697
Availability:
Rights:
open access
Accession Number:
edsbas.CFCD3ED8
Database:
BASE
*Further Information*
*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.*