IMPLEMENTATION OF GENETIC ALGORITHM FOR NEURAL NETWORK OPTIMIZATION IN THE CASE STUDY OF THE TRON GAME

  • Muhammad Darmadi FMIPA ULM
  • Irwan Budiman FMIPA ULM
  • Muliadi FMIPA ULM
  • Andi Farmadi FMIPA ULM
  • Triando Hamonangan Saragih FMIPA ULM
Keywords: Games, Genetics, Neural networks, Artificial intelligence, Tron

Abstract

Abstract

 

Tron is played in an arena composed of grids and often both players are placed at different starting points, each player basically playing the game by aiming straight, turning left or turning right until one or both of them hit a wall or laser object. This study aims to examine how good genetic algorithms are in optimizing neural networks for artificial intelligence. As well as to find out what the winning percentage is for each researched artificial intelligence. The results obtained are that N5 is faster in obtaining optimal results, which only requires 9 generations but has the lowest percentage. So it can be concluded that the faster finding optimal results does not guarantee that artificial intelligence will be better..

Published
2022-12-28
How to Cite
Darmadi, M., Irwan Budiman, Muliadi, Andi Farmadi, & Triando Hamonangan Saragih. (2022). IMPLEMENTATION OF GENETIC ALGORITHM FOR NEURAL NETWORK OPTIMIZATION IN THE CASE STUDY OF THE TRON GAME. Journal of Data Science and Software Engineering, 3(02), 76-87. Retrieved from https://jurnalmahasiswamipa.ulm.ac.id/index.php/integer/article/view/73
Issue
Vol. 3 No. 02 (2022)
Section
Articles