Analysis of selected methods of creating artificial intelligence on the example of a popular card game
The aim of the article was to analyze selected methods of creating artificial intelligence in a popular card game. Two experiments were conducted: with a human and with a computer. The following algorithms were analyzed: random, min-max, based on a neural network, statistical and statistical with th...
Uloženo v:
| Vydáno v: | Journal of Computer Sciences Institute Ročník 16; s. 233 - 240 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Lublin University of Technology
30.09.2020
|
| Témata: | |
| ISSN: | 2544-0764, 2544-0764 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Shrnutí: | The aim of the article was to analyze selected methods of creating artificial intelligence in a popular card game. Two experiments were conducted: with a human and with a computer. The following algorithms were analyzed: random, min-max, based on a neural network, statistical and statistical with the use of "cheating" technique. The examined parameters were as follows: efficiency, execution time, number of implementation code lines, implementation time and training duration. The indicator with the greatest impact on the selection of the most optimal method was efficiency. The research has shown no difference in efficiency for the neural network-based algorithm and the statistical algorithm. In other cases, the differences in this feature were significant. The use of the "cheating" technique has increased the efficiency. |
|---|---|
| ISSN: | 2544-0764 2544-0764 |
| DOI: | 10.35784/jcsi.2194 |