New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Agent za igricu 2048 #23

Open

KatarinaM-SV6 opened this issue May 11, 2023 · 2 comments

Labels

Branislav Anđelić Marko Njegomir Tema odobrena

KatarinaM-SV6 commented May 11, 2023 •

edited

Loading

Članovi tima:

Katarina Mirković, SV6/2020, grupa 1
Jana Nikolić, SV19/2020, grupa 2

Asistent:

Marko Njegomir
Branislav Anđelić

Problem koji se rešava:

Potrebno je napraviti agenta za igranje igrice 2048, koji poredi postignute rezultate 2 algoritma: Monte Karlo i Deep Reiforcement Learning u odnosu na random agenta, kao i različite načine evaluacije tabele i koji dovode do najboljeg rešenja

2048

Algoritam/algoritmi:

Monte Carlo Tree Search
Deep Reinforcement Learning
Random agent

Metrika za merenje performansi:

Najveći ostvaren broj polja
Suma svih polja tabele na kraju
Zbir vrednosti za sve kvadrate koji su se spojili tokom igre

Validacija rešenja:

Provera da li agent bira validne poteze
Provera da li agent bira potez koji će osvojiti najviše bodova

bandjeo added Branislav Anđelić Marko Njegomir labels

bandjeo added the Tema odobrena label

Contributor

bandjeo commented May 23, 2023

Tema odobrena. Ostavite link ka github repozitorijumu.

Srećan ran!

Author

KatarinaM-SV6 commented Jul 4, 2023

https://github.com/JanaNikolic/2048-bot

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment