Fulltext available Open Access
Title: Exploration of Reinforcement Learning Methods when Training a Dice Game Playing Agent
Language: English
Authors: Alushi, Klejda 
Keywords: Artificial Intelligence; Deep Learning; Reinforcement Learning; Dice Game; Advantage Actor Critic
Issue Date: 26-Jul-2024
Abstract: 
This thesis will use different reinforcement learning algorithms to train a neural network to play a dice game. It will analyse how these algorithms are influenced by stochastic processes and by the dimensions of the neural network.

Diese Bachelorarbeit wird verschiedene Reinforcement-Learning-Algorithmen verwenden, um ein neuronales Netzwerk darauf zu trainieren, ein Wuerfelspiel zu spielen. Es wird analysiert, wie diese Algorithmen durch stochastische Prozesse und durch die Dimensionen des neuronalen Netzes beeinflusst werden.
URI: https://hdl.handle.net/20.500.12738/16102
Institute: Fakultät Technik und Informatik 
Department Informations- und Elektrotechnik 
Type: Thesis
Thesis type: Bachelor Thesis
Advisor: Hensel, Marc  
Referee: Herster, Ulrike 
Appears in Collections:Theses

Files in This Item:
File Description SizeFormat
BA_Exploration_Reinforcement_Learning_Methods.pdf2.03 MBAdobe PDFView/Open
Show full item record

Page view(s)

32
checked on Nov 24, 2024

Download(s)

55
checked on Nov 24, 2024

Google ScholarTM

Check

HAW Katalog

Check

Note about this record


Items in REPOSIT are protected by copyright, with all rights reserved, unless otherwise indicated.