anh-nn01/Lunar-Lander-Double-Deep-Q-Networks

An AI agent that use Double Deep Q-learning to teach itself to land a Lunar Lander on OpenAI universe

38
/ 100
Emerging

This project offers an AI agent that teaches itself how to land a virtual lunar lander safely and quickly on a designated landing pad. By observing its actions and receiving feedback on its performance, the agent learns to control the lander's thrusters. This tool is designed for AI researchers and enthusiasts who are exploring reinforcement learning techniques.

No commits in the last 6 months.

Use this if you are studying or experimenting with reinforcement learning and want to see how a Double Deep Q-Network can solve a control problem like landing a spacecraft.

Not ideal if you are looking for a practical tool to control real-world spacecraft or for a simple simulation without deep learning.

Reinforcement Learning AI Agent Game AI Deep Q-Networks Spacecraft Control Simulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

17

Forks

6

Language

Python

License

MIT

Category

lunar-lander-rl

Last pushed

Mar 15, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks"

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