FelipeMarcelino/2048-Gym
This projects aims to use reinforcement learning algorithms to play the game 2048.
This project offers a reinforcement learning solution to play the game 2048. It takes in game board states as input and outputs optimal moves to achieve high scores, aiming to reach the 2048 tile. It's designed for machine learning researchers or enthusiasts interested in applying and experimenting with deep Q-learning algorithms in a classic game environment.
No commits in the last 6 months.
Use this if you are a machine learning researcher or student looking to explore and apply reinforcement learning, specifically DQN, to a grid-based puzzle game.
Not ideal if you are a casual player simply looking for a bot to play 2048 for you without delving into the underlying AI algorithms.
Stars
88
Forks
13
Language
Python
License
—
Category
Last pushed
Nov 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/FelipeMarcelino/2048-Gym"
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...
SrinidhiRaghavan/AI-2048-Puzzle
2048 puzzle using minimax algorithm
moporgic/TDL2048
The Most Efficient Temporal Difference Learning Framework for 2048