Thesis Details

Hluboké učení AI v herních prostředích

Bachelor's Thesis Student: Glós Kristián Academic Year: 2020/2021 Supervisor: Polášek Tomáš, Ing.
Language
Slovak
Abstract

This thesis is focused on analysing deep learning algorithms and their ability to complete given tasks implemented in game environments created via the Unity game engine. Secondary objective was to research and specify possible use-cases of deep learning during game development. The algorithms used fall into Reinforcement learning, Imitation learning and Neuroevolution, while Reinforcement learning was used throughout the whole game scene development cycle. Analysis and results were collected through training the networks in different game scene states and other factors.

Keywords

Deep Learning, Machine learning, AI, Reinforcement Learning, Imitation Learning, GAIL, Q-Learning, Proximal Policy Optimalization,  ML-agents, Unity, Game environments, Agents, rewards and penalties, Genetic Algorithms, Neuroevolution, Neuroevolution of Augmented Topologies, Evolution Strategies, Markov Decision Process, Neural network

Department
Degree Programme
Information Technology
Files
Status
defended, grade D
Date
15 June 2021
Reviewer
Committee
Zbořil František, doc. Ing., Ph.D. (DITS FIT BUT), předseda
Hradiš Michal, Ing., Ph.D. (DCGM FIT BUT), člen
Kekely Lukáš, Ing., Ph.D. (DCSY FIT BUT), člen
Rogalewicz Adam, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Veselý Vladimír, Ing., Ph.D. (DIFS FIT BUT), člen
Citation
GLÓS, Kristián. Hluboké učení AI v herních prostředích. Brno, 2021. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2021-06-15. Supervised by Polášek Tomáš. Available from: https://www.fit.vut.cz/study/thesis/24101/
BibTeX
@bachelorsthesis{FITBT24101,
    author = "Kristi\'{a}n Gl\'{o}s",
    type = "Bachelor's thesis",
    title = "Hlubok\'{e} u\v{c}en\'{i} AI v hern\'{i}ch prost\v{r}ed\'{i}ch",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2021,
    location = "Brno, CZ",
    language = "slovak",
    url = "https://www.fit.vut.cz/study/thesis/24101/"
}
Back to top