JohDonald/Deep-Q-Learning-Deep-SARSA-LunarLander-v2

Applying deep reinforcement learning algorithms, Deep SARSA and Deep Q-Learning, to OpenAI Gym's LunarLander-v2.

25
/ 100
Experimental

This project explores how to teach an AI to safely land a lunar module in a simulated environment. It takes data like the module's position and velocity, along with whether its legs are touching the ground, and produces a trained AI that knows the best actions to take (like firing thrusters) to land successfully. This is useful for researchers and students working on reinforcement learning and autonomous control.

No commits in the last 6 months.

Use this if you are a researcher or student interested in understanding and applying deep reinforcement learning algorithms like Deep Q-Learning and Deep SARSA to a control problem.

Not ideal if you are looking for a plug-and-play solution for a real-world autonomous landing system or a different type of AI problem.

reinforcement-learning autonomous-control AI-training simulated-environments robotics-education
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Jupyter Notebook

License

Category

lunar-lander-rl

Last pushed

Apr 09, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JohDonald/Deep-Q-Learning-Deep-SARSA-LunarLander-v2"

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