tsangwpx/ml2048
Yet another 2048 in reinforcement learning
This project helps you train an AI agent to play the game 2048. It takes the game board as input and produces optimal moves, allowing the AI to achieve high scores. This is for machine learning researchers and enthusiasts interested in applying and experimenting with deep reinforcement learning techniques.
No commits in the last 6 months.
Use this if you are a machine learning practitioner looking for a practical example and implementation of advanced reinforcement learning algorithms like PPO and Actor-Critic for game AI.
Not ideal if you are simply looking for the best possible 2048 solver, as other methods like n-tuple networks or expectimax optimization can achieve even higher scores.
Stars
8
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tsangwpx/ml2048"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Kulbear/endless-2048
[WIP] Aim to build an AI player for the 2048 game with a remarkable winning rate.
lesaun/2048-expectimax-ai
2048 game solved with Expectimax
qpwoeirut/2048-solver
A set of AIs for the 2048 tile-merging game. Includes an expectimax strategy that reaches 16384...
FelipeMarcelino/2048-Gym
This projects aims to use reinforcement learning algorithms to play the game 2048.
SrinidhiRaghavan/AI-2048-Puzzle
2048 puzzle using minimax algorithm