MehdiShahbazi/DQN-Frozenlake-Gymnasium

This repo implements Deep Q-Network (DQN) for solving the Frozenlake-v1 environment of the Gymnasium library using Python 3.8 and PyTorch 2.0.1 in both 4x4 and 8x8 map sizes.

26
/ 100
Experimental

This project helps demonstrate how a computer agent can learn to navigate a simple environment, like moving across a frozen lake to a goal, without falling into holes. It takes the agent's current location as input and produces the best next move. This is for anyone interested in understanding the basics of how artificial intelligence learns optimal strategies through trial and error.

No commits in the last 6 months.

Use this if you are learning about reinforcement learning and want to see a practical example of the Deep Q-Network (DQN) algorithm applied to a basic navigation problem.

Not ideal if you are looking for a plug-and-play solution for complex, real-world robotic navigation or game AI that requires highly optimized performance and stability.

AI learning Reinforcement learning Pathfinding Agent training Decision making
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

21

Forks

1

Language

Python

License

MIT

Category

lunar-lander-rl

Last pushed

Mar 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MehdiShahbazi/DQN-Frozenlake-Gymnasium"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.