juliankappler/lunar-lander

Implementation of deep reinforcement learning algorithms for training an agent to play the game lunar lander

32
/ 100
Emerging

This project helps machine learning researchers explore and compare deep reinforcement learning algorithms for training an agent to successfully land a lunar module. It takes in various algorithm parameters and outputs a trained agent capable of playing the Lunar Lander game, along with performance statistics. Researchers and students in AI or control systems would use this to understand algorithm trade-offs.

No commits in the last 6 months.

Use this if you are a researcher or student interested in experimenting with and comparing Actor-Critic and Deep Q-Learning algorithms for a control task.

Not ideal if you need a production-ready solution for complex aerospace control or want to apply reinforcement learning to a different problem domain without modification.

reinforcement-learning-research game-AI algorithm-comparison control-systems AI-education
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

38

Forks

10

Language

Jupyter Notebook

License

Category

lunar-lander-rl

Last pushed

May 15, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/juliankappler/lunar-lander"

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