Institutional Repository of Vilnius University
Dirbtiniai neuroniniai tinklai žaidimuose /
Abstract
dc:descriptionIn this work the author analyzes the usage of artificial neural networks in games. The author also analyzes several models of artificial neural network learning, supervised learning and reinforcement learning, and compare their application for creating an artificial neural network, designed for games. From the artificial neural network learning models that are analyzed, supervised learning is chosen to implement practically, to create and train a neural network, capable of playing a clone of the game „Bomberman“. To train the final agent, about 100000 pairs of training data is used, from which the neural network learns the basics of the game and manages to win games against the computer controlled agent that is built-into the game.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kvašinskas, Rytautas,
- Contributors dc:contributor
-
- Dapkūnas, Boleslovas
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:ELABAETD107116035&prefLang=en_US