Please use this identifier to cite or link to this item:
Title: Non-parametric Models and Contextual Policy Search for More Efficient Robot Skill Generalization
Keywords: gaussian process, policy search, robot skill learning, skill generalization, kernel embedding of distributions, robot learning
Issue Date: 21-Jan-2014
Citation: ANDRAS GABOR KUPCSIK (2014-01-21). Non-parametric Models and Contextual Policy Search for More Efficient Robot Skill Generalization. ScholarBank@NUS Repository.
Abstract: Robot skill learning is a promising alternative to hand designing controllers that encode the skill. However, most learning algorithms are highly data-inefficient and cannot generalize to unseen situations efficiently. In order to scale robot skill learning algorithms to more complex tasks we address the above challenges in this thesis. Firstly, we evaluate the contextual extension of the Relative Entropy Policy Search (REPS) algorithm on complex robot learning tasks. Secondly, we propose a model-based extension of the contextual REPS algorithm to address data-efficiency. We investigate how Gaussian Process (GP) models can be used for model learning and trajectory prediction, and how we can incorporate models in the REPS learning framework. We present a novel probabilistic model learning framework with a special focus on learning models for long-term trajectory prediction. Finally, we investigate how model learning and trajectory prediction can be evaluated in feature spaces with kernel embedding of conditional distributions.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
KupcsikA.pdf12.86 MBAdobe PDF



Page view(s)

checked on Oct 5, 2018


checked on Oct 5, 2018

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.