Jezik: | Slovenski jezik |
---|---|
Leto izida: | 2022 |
Tipologija: | 2.11 - Diplomsko delo |
Organizacija: | UM FERI - Fakulteta za elektrotehniko, računalništvo in informatiko |
Založnik: | [M. Polner] |
UDK: | 004.8:004.94(043.2) |
COBISS: |
139102979
![]() |
Št. ogledov: | 136 |
Št. prenosov: | 22 |
Ocena: | 0 (0 glasov) |
Metapodatki: |
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Sekundarni jezik: | Angleški jezik |
---|---|
Sekundarni naslov: | Teaching a neural network to play a simple arcade game |
Sekundarni povzetek: | The thesis aimed to create a neural network and a simple arcade video game called Bomberman that the neural network would learn to play. The video game was created using the open-source framework LibGdx in the Java programming language. We implemented our own neural network and a neural network based on the PyTorch library. Both networks learn using the reinforcement learning method. The results of our own implementation of the neural network were compared with the results of the neural network implemented with the PyTorch library. We found that the results of both networks are very similar. After thirty minutes of learning, the neural network manages to clear half of all destructible walls. |
Sekundarne ključne besede: | arcade video game;Bomberman;neural network;reinforcement learning;deep Q-network; |
Vrsta dela (COBISS): | Diplomsko delo/naloga |
Komentar na gradivo: | Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije |
Strani: | 1 spletni vir (1 datoteka PDF (X, 48 f.)) |
ID: | 16374780 |