Efficient Reinforcement Learning Using Gaussian Processes

Efficient Reinforcement Learning Using Gaussian Processes
Author :
Publisher : KIT Scientific Publishing
Total Pages : 226
Release :
ISBN-10 : 9783866445697
ISBN-13 : 3866445695
Rating : 4/5 (695 Downloads)

Book Synopsis Efficient Reinforcement Learning Using Gaussian Processes by : Marc Peter Deisenroth

Download or read book Efficient Reinforcement Learning Using Gaussian Processes written by Marc Peter Deisenroth and published by KIT Scientific Publishing. This book was released on 2010 with total page 226 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.


Efficient Reinforcement Learning Using Gaussian Processes Related Books

Efficient Reinforcement Learning Using Gaussian Processes
Language: en
Pages: 226
Authors: Marc Peter Deisenroth
Categories: Electronic computers. Computer science
Type: BOOK - Published: 2010 - Publisher: KIT Scientific Publishing

DOWNLOAD EBOOK

This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fu
Gaussian Processes for Machine Learning
Language: en
Pages: 266
Authors: Carl Edward Rasmussen
Categories: Computers
Type: BOOK - Published: 2005-11-23 - Publisher: MIT Press

DOWNLOAD EBOOK

A comprehensive and self-contained introduction to Gaussian processes, which provide a principled, practical, probabilistic approach to learning in kernel machi
Algorithms for Reinforcement Learning
Language: en
Pages: 89
Authors: Csaba Grossi
Categories: Computers
Type: BOOK - Published: 2022-05-31 - Publisher: Springer Nature

DOWNLOAD EBOOK

Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a lon
Reinforcement Learning, second edition
Language: en
Pages: 549
Authors: Richard S. Sutton
Categories: Computers
Type: BOOK - Published: 2018-11-13 - Publisher: MIT Press

DOWNLOAD EBOOK

The significantly expanded and updated new edition of a widely used text on reinforcement learning, one of the most active research areas in artificial intellig
Artificial Intelligence and Statistics
Language: en
Pages: 440
Authors: William A. Gale
Categories: Computers
Type: BOOK - Published: 1986 - Publisher: Addison Wesley Publishing Company

DOWNLOAD EBOOK

A statistical view of uncertainty in expert systems. Knowledge, decision making, and uncertainty. Conceptual clustering and its relation to numerical taxonomy.