| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font
First page > Show document

Show document Help

Title:Globoko okrepitveno učenje za igranje iger na podlagi video vhoda : magistrsko delo
Authors:ID Bozhinova, Monika (Author)
ID Strnad, Damjan (Mentor) More about this mentor... New window
Files:.pdf MAG_Bozhinova_Monika_2021.pdf (2,16 MB)
MD5: A8555C713D5D6B97A0BAA03C1473C248
PID: 20.500.12556/dkum/5d9a358e-6fb9-42ab-973f-584c0d32e4a4
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V magistrskem delu smo se ukvarjali z okrepitvenim učenjem agentov za igranje računalniških iger. V ta namen smo implementirali tri modele agenta, ki temeljijo na uporabi nevronske mreže za aproksimacijo funkcije vrednosti akcij, in predlagali lastno izboljšano arhitekturo dvobojevalne dvojne Q-mreže. Učenje smo izvajali na igrah Pong in Beamrider iz nabora iger Atari 2600. Ugotovili smo, da z našim pristopom dosežemo boljšo zmogljivost agenta kot globoka Q-mreža, dvojna globoka Q-mreža in dvojna globoka Q-mreža z dvobojevalno arhitekturo v igri Pong, medtem ko se v igri Beamrider agent uči počasneje, predvidoma zaradi šuma v drugačni predstavitvi stanja, ki ga predlagani model uporablja.
Keywords:globoko okrepitveno učenje, nevronske mreže, globoka Q-mreža, dvobojevalna arhitektura, igre Atari, Pong, Beamrider
Place of publishing:Maribor
Place of performance:Maribor
Publisher:M. Bozhinova]
Year of publishing:2021
Number of pages:XII, 52 str.
PID:20.500.12556/DKUM-80671 New window
UDC:004.85:004.96(043.2)
COBISS.SI-ID:83074563 New window
Publication date in DKUM:20.10.2021
Views:974
Downloads:90
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
BOZHINOVA, Monika, 2021, Globoko okrepitveno učenje za igranje iger na podlagi video vhoda : magistrsko delo [online]. Master’s thesis. Maribor : M. Bozhinova. [Accessed 18 April 2025]. Retrieved from: https://dk.um.si/IzpisGradiva.php?lang=eng&id=80671
Copy citation
  
Average score:
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Searching for similar works...Please wait....
Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY 4.0, Creative Commons Attribution 4.0 International
Link:http://creativecommons.org/licenses/by/4.0/
Description:This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.
Licensing start date:28.09.2021

Secondary language

Language:English
Title:Deep reinforcement learning for playing games based on video input
Abstract:In the master's thesis, we dealt with reinforcement learning of agents for playing computer games. To this end, we implemented three agent models based on the use of neural networks as action value function approximators, and proposed our own improved architecture of the dueling double Q-network. We conducted the training on the games Pong and Beamrider from the Atari 2600 games. We found that with our approach we achieve better agent performance than deep Q-networks, double deep Q-networks and double deep Q-networks with dueling architecture in the game Pong, while in Beamrider the agent learns more slowly, presumably due to the noise in the different representation of the state used by the proposed model.
Keywords:deep reinforcement learning, neural networks, deep Q-network, dueling architecture, Atari games, Pong, Beamrider


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica