Transfer learning for deep neural nets
Umé, Benoît
Promotor(s) : Ernst, Damien ; Aittahar, Samy
Date of defense : 25-Jun-2018/26-Jun-2018 • Permalink : http://hdl.handle.net/2268.2/4678
Details
Title : | Transfer learning for deep neural nets |
Author : | Umé, Benoît |
Date of defense : | 25-Jun-2018/26-Jun-2018 |
Advisor(s) : | Ernst, Damien
Aittahar, Samy |
Committee's member(s) : | Castronovo, Michaël
Louppe, Gilles Hiard, Samuel |
Language : | English |
Keywords : | [en] transfer [en] learning [en] mountain [en] car [en] cartpole [en] neural [en] network [en] concatenation [en] merge [en] openai [en] gym [en] reinforcement |
Discipline(s) : | Engineering, computing & technology > Computer science |
Institution(s) : | Université de Liège, Liège, Belgique |
Degree: | Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems" |
Faculty: | Master thesis of the Faculté des Sciences appliquées |
Abstract
[en] The objective of this master thesis is to find transfer learning
methods which can be applied in reinforcement learning problems.
This method has to improves the learning speed of an agent on a
target task, given a set of already trained policies on similar
simpler tasks. We used Q learning algorithm combined to neural
network to represent Q function that determine how an agent act
on it’s assigned task.
Using source network trained on simpler problems, we manage to
find an architecture that combines networks with an interface to
transfer knowledge in the new network. This technique allowed us
to solve the OpenAI Gym mountain car problem using source
networks trained on a smaller mountain and a faster car.
We tested more complex connection architectures to improve the
representation complexity of the combined networks.
We also implemented a method to learn multiple networks in
parallel to exploit the ensemble properties when learning a new
task. This method improves the convergence and results.
Finally we tested our implementation on the OpenAI Gym
Cartpole environment with succes.
File(s)
Document(s)
Annexe(s)
Cite this master thesis
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.