Efficient Reinforcement Learning using Gaussian Processes

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...

Täydet tiedot

Tallennettuna:
Bibliografiset tiedot
Päätekijä: Deisenroth, Marc Peter (auth)
Aineistotyyppi: Elektroninen Kirjan osa
Kieli:englanti
Julkaistu: KIT Scientific Publishing 2010
Sarja:Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory
Aiheet:
Linkit:DOAB: download the publication
DOAB: description of the publication
Tagit: Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!

Internet

DOAB: download the publication
DOAB: description of the publication

3rd Floor Main Library

Saatavuus: 3rd Floor Main Library
Hyllypaikka: A1234.567
Nide 1 Saatavissa