Search results: Found 2

Listing 1 - 2 of 2
Sort by
Efficient Reinforcement Learning using Gaussian Processes

Author:
Book Series: Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory ISSN: 18673813 ISBN: 9783866445697 Year: Volume: 9 Pages: IX, 205 p. DOI: 10.5445/KSP/1000019799 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Computer Science
Added to DOAB on : 2019-07-30 20:02:01
License:

Loading...
Export citation

Choose an application

Abstract

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.

Flow control : theoretical concept of absolute instability

Author:
ISBN: 9783866445314 Year: Pages: 97 p. DOI: 10.5445/KSP/1000016554 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Technology (General)
Added to DOAB on : 2019-07-30 20:01:58
License:

Loading...
Export citation

Choose an application

Abstract

At the 37th Prandtl memorial lecture on Regions of Viccous Flow, H.Oertel 1994 developed for the first time the stability theory of local perturbations in boundary layers and wake flows, as well as their practical application in the flow control of vehicle flows and the boundary layer of civil aircraft wings.This work presents how the stability theory concept of absolute instability has advanced and proven in practice in the last 15 years in terms of the efficient flow control.

Listing 1 - 2 of 2
Sort by
Narrow your search

Publisher

KIT Scientific Publishing (2)


License

CC by-nc-nd (2)


Language

english (2)


Year
From To Submit

2010 (2)