Result: Efficient Reinforcement Learning using Gaussian Processes
Title:
Efficient Reinforcement Learning using Gaussian Processes
Authors:
Contributors:
Hanebeck, UD
Publisher Information:
KIT Scientific Publishing, 2010.
Publication Year:
2010
Subject Terms:
Document Type:
Book
Book
File Description:
image/jpeg; IX, 205 páginas; application/pdf
Language:
English
DOI:
10.5445/ksp/1000019799
Access URL:
Rights:
CC BY NC ND
Accession Number:
edsair.dedup.wf.002..23e5d43c0944e9fbebebad649f3f736b
Database:
OpenAIRE
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.