prikaz prve stranice dokumenta Predator-prey simulation using neuroevolution for agent development
  Download
PDF 1.09 MB
master's thesis
Predator-prey simulation using neuroevolution for agent development
2023. urn:nbn:hr:190:822305
Vargić, Anamaria
University of Rijeka
Faculty of Engineering

Cite this document

Vargić, A. (2023). Predator-prey simulation using neuroevolution for agent development (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:822305

Vargić, Anamaria. "Predator-prey simulation using neuroevolution for agent development." Master's thesis, University of Rijeka, Faculty of Engineering, 2023. https://urn.nsk.hr/urn:nbn:hr:190:822305

Vargić, Anamaria. "Predator-prey simulation using neuroevolution for agent development." Master's thesis, University of Rijeka, Faculty of Engineering, 2023. https://urn.nsk.hr/urn:nbn:hr:190:822305

Vargić, A. (2023). 'Predator-prey simulation using neuroevolution for agent development', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 03 May 2024, https://urn.nsk.hr/urn:nbn:hr:190:822305

Vargić A. Predator-prey simulation using neuroevolution for agent development [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2023 [cited 2024 May 03] Available at: https://urn.nsk.hr/urn:nbn:hr:190:822305

A. Vargić, "Predator-prey simulation using neuroevolution for agent development", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:190:822305

Please login to the repository to save this object to your list.
Metadata
TitlePredator-prey simulation using neuroevolution for agent development
AuthorAnamaria Vargić
MentorGoran Mauša (mentor)
Committee memberIvo Ipšić (predsjednik povjerenstva)
Committee memberSandi Ljubić (član povjerenstva)
Committee memberGoran Mauša (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
Rijeka
Defense date and country2023-11-21, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
This thesis shows the creation of a predator-prey simulation, where entities move autonomously using neural networks. The NEAT algorithm is used in order to obtain the best performing neural networks for each entity type. Predators are first trained using static prey, after which these predators are used to train prey to flee. The best neural networks obtained by training are then put into a visualized test environment to observe their behavior. Pursuit and evasion behavior is successfully achieved, and it is observed that the most important role in successfully applying NEAT are the activation function, fitness function and output interpretation in regards to the given inputs.
Keywords
Languageenglish
URN:NBNurn:nbn:hr:190:822305
Study programmeTitle: Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2023-11-17 07:45:19