| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:KOEVOLUCIJA IGRALCEV V IGRI TOWER DEFENSE
Authors:ID Chuchurski, Viktor (Author)
ID Strnad, Damjan (Mentor) More about this mentor... New window
Files:.pdf UNI_Chuchurski_Viktor_2014.pdf (1,07 MB)
MD5: BB6A0C5D851224DB3966F13EC8E421EF
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V diplomskem delu opišemo implementacijo tekmovalne koevolucije dveh nasprotujočih populacij računalniških igralcev v igri Tower Defense. Prvo populacijo predstavljajo računalniške pošasti, ki se gibljejo proti določenemu cilju na igralnem polju. Njihova naloga je uspešno priti do cilja, s čemer zmanjšujejo zdravje nasprotnika. Druga populacija so stolpi, ki streljajo na pošasti in jih krmili igralec. Cilj igralca je strateško postaviti stolpe, da bi uspešno preprečili pošastim priti do cilja. V naši nalogi dva genetska algoritma krmilita ti dve populaciji. Z uporabo koevolucije izmenično prilagajamo obe populaciji njunim nasprotnikom. Rezultati pokažejo, da je konvergenca k stabilnemu stanju odvisna od uporabljenih parametrov genetskega algoritma in da se vsaka populacija obnaša na specifičen način pri določenih vrednostih parametrov.
Keywords:genetski algoritem, koevolucija, računalniška igra, Tower Defense, stolpi, pošasti
Place of publishing:Maribor
Publisher:[V. Chuchurski]
Year of publishing:2014
PID:20.500.12556/DKUM-45749 New window
UDC:004.421:004.92(043.2)
COBISS.SI-ID:19164182 New window
NUK URN:URN:SI:UM:DK:HKZRUG5Y
Publication date in DKUM:06.11.2015
Views:1645
Downloads:126
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:COEVOLUTION OF PLAYERS IN GAME TOWER DEFENSE
Abstract:This diploma discribes the implementation of competitive coevolution of two opposing populations in a Tower Defense game. The first population is composed of monsters which move from one side of the board to a predefined goal. Their task is to reach the goal, which decreases the opponent's health. The other population are the towers that shoot the monsters and are controlled by the player. The player's task is to strategically place the towers, so that they will kill all the monsters before they reach the goal. In our implemetation the two populations are controlled by two genetic algorithms. Coevolution will evolve both populations. The results show that the population's avarege score convergence is conditioned by the genetic algorithm parameters. They also demonstrate that both generations have specific behaviours for certain values of the algorithm parameters.
Keywords:genetic algorithm, coevolution, computer game, Tower Defense, towers, monsters


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