Thesis Details

Posilované učení pro hraní robotického fotbalu

Bachelor's Thesis Student: Brychta Adam Academic Year: 2019/2020 Supervisor: Smrž Pavel, doc. RNDr., Ph.D.
English title
Reinforcement Learning for Robotic Soccer Playing
Language
Czech
Abstract

The aim of this thesis is to create a reinforcement learning agent that is able to play a soccer. I'm working with the deep Q-learning algorithm, which uses deep neural network. The practical part of this work is about implementing the agent for reinforcement learning. The goal of the agent is to choose the best action possible for a given situation. The agent is being trained in a variety of scenarios. The result of this thesis shows an approach to control soccer player using machine learning.

Keywords

reinforcement learning, reinforcement learning for soccer, Q-learning, deep Q-learning, double deep Q-learning

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology
Files
Status
defended, grade B
Date
13 July 2020
Reviewer
Švec Tomáš, Ing.
Committee
Zbořil František, doc. Ing., Ph.D. (DITS FIT BUT), předseda
Grégr Matěj, Ing., Ph.D. (DIFS FIT BUT), člen
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
Citation
BRYCHTA, Adam. Posilované učení pro hraní robotického fotbalu. Brno, 2020. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2020-07-13. Supervised by Smrž Pavel. Available from: https://www.fit.vut.cz/study/thesis/22795/
BibTeX 
@bachelorsthesis{FITBT22795,
    author = "Adam Brychta",
    type = "Bachelor's thesis",
    title = "Posilovan\'{e} u\v{c}en\'{i} pro hran\'{i} robotick\'{e}ho fotbalu",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2020,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/22795/"
}

Theses

Back to top