Institutional Repository of Vilnius University
Skatinamojo mokymo paremto neuroninias tinklais optimizavimas taikant žinių pernešimą /
Abstract
dc:descriptionOptimizing Deep Reinforcement Learning Process by Applying Transfer Learning. In this thesis we try to apply transfer learning to deep reinforcement learning, to optimize and speed up the learning process of an agent. The thesis reviews machine learning types and branches. The history of reinforcement learning is also briefly covered, together with the needed theory and algorithms for the experiments. We also take a look at the environments, frameworks and tools that we use to train agents and construct artificial neural networks. At the end of the thesis we complete four experiments, to evaluate if we can optimize deep reinforcement learning by applying transfer learning.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Jakimčikas, Martynas,
- Contributors dc:contributor
-
- Grevys, Andrius
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD81806029&prefLang=en_US