SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document

Title:Primerjava in razvoj pristopov računske inteligence za spletno platformo igre Travian: Kingdoms
Authors:Šantl, Mitja (Author)
Zamuda, Aleš (Mentor) More about this mentor... New window
Files:.pdf MAG_Santl_Mitja_2018.pdf (2,86 MB)
 
.zip MAG_Santl_Mitja_2018.zip (485,80 KB)
 
Language:Slovenian
Work type:Master's thesis/paper (mb22)
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V magistrskem delu se ukvarjamo z nalogo spletnih agentov za igro Travian: Kingdoms. V ta namen razvijemo razširitev za brskalnik, ki deluje v brskalniku Google Chrome in ima sposobnost opravljanja osnovnih akcij v igri, na primer: gradnja, napadanje in trgovanje. Posebno pozornost posvetimo gradnji, kjer želimo poiskati optimalen vrstni red gradbenih nalog. Zaradi kompleksnosti naloge izdelave takega agenta preučimo aplikativnost domene računske inteligence za naš primer. Za spletno platformo igre Travian: Kingdoms tako razvijemo in primerjamo pristope s petimi algoritmi: algoritmom mehke logike, algoritmom diferencialne evolucije, naključnim algoritmom, algoritmom izčrpnega iskanje in požrešnim algoritmom. Na podlagi primerjave rezultatov pristopov ugotovimo, da ima vsak algoritem svoje prednosti in slabosti. V okviru naše naloge se najbolje odreže pristop z algoritmom diferencialne evolucije.
Keywords:računska inteligenca, spletni agent, razširitev spletnega brskalnika, računalniška igra Travian: Kingdoms, spletni brskalnik, večkriterijska optimizacija, računska inteligenca
Year of publishing:2018
Source:Maribor
License:CC BY-NC-ND 4.0
This work is available under this license: Creative Commons Attribution Non-Commercial No Derivatives 4.0 International
Views:21
Downloads:3
Metadata:XML RDF-CHPDL DC-XML DC-RDF
Categories:KTFMB - FERI
:
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

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:Comparison and development of computational intelligence approaches for web platform of the game Travian: Kingdoms
Abstract:In this work, the case of web agents for Travian: Kingdoms game are studied. For this purpose, a browser extension is developed that works in web browser Google Chrome and has an ability to preform basic actions in the game Travian: Kingdoms like build, attack, and trade. Special attention is given to action build, to find an optimal order of building tasks. Due to the complexity of the problem to develop such agent, applicability of the domain of computational intelligence to our case is examined. For web platform of the game Travian: Kingdoms approches using five algorithms are developed and compared: fuzzy logic algorithm, differencial evolution algorithm, a randomized angorithm, algorithm exhaustive search, and greedy algorithm. Based on the comparison of the results we come to conclusion that each of these approaches has its own strong and weak points. In our case the overall winner is differencial evolution algorithm.
Keywords:computional intelligence, web bot, browser extension, computer game Travian: Kingdoms, web browser, multi-objective optimization, computional intelligence


Comments

Leave comment

You have to 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