Thesis Details
Sběratelská karetní hra s umělou inteligencí
The aim of this thesis is a digital version of a card game Flesh and Blood. The element of the game is artificial intelligence which can play the game at a beginner level. The essential issue with creating the game and its artificial intelligence is the fact that the game is constantly expanding with new cards and rules.The thesis describes how could this progress be solved in such dynamic enviroment. The issue with expansion of the game is solved by encapsulated modules for each game element.This approach simplifies the addition of new cards and possible modification of rules. A possible solution for artificial intelligence is suitable adaptation of inputs.Artificial intelligence is realized by means of a neural network and taught by self play or with other networks. The output of the network is the selection of a suitable move, which takes place on the basis of information about the current state of the game. Therefore, it is important to effectively encode the current state of the game board.
artificial inteligence, game, card game, neural network, ML-Agents, Unity, Flesh and Blood
Bařina David, Ing., Ph.D. (DCGM FIT BUT), člen
Češka Milan, doc. RNDr., Ph.D. (DITS FIT BUT), člen
Grézl František, Ing., Ph.D. (DCGM FIT BUT), člen
Milet Tomáš, Ing., Ph.D. (DCGM FIT BUT), člen
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT), člen
@mastersthesis{FITMT25072, author = "Josef Dole\v{z}al", type = "Master's thesis", title = "Sb\v{e}ratelsk\'{a} karetn\'{i} hra s um\v{e}lou inteligenc\'{i}", school = "Brno University of Technology, Faculty of Information Technology", year = 2022, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/25072/" }