taherfattahi/ppo-rocket-landing

Proximal Policy Optimization (PPO) algorithm using PyTorch to train an agent for a rocket landing task in a custom environment

48
/ 100
Emerging

Implements a physics-based rocket environment with 8-dimensional state vectors (position, velocity, angle, nozzle orientation) and 9 discrete actions combining three thrust levels with nozzle angular velocities, enabling the agent to learn hover and landing control. Features separate actor-critic networks with configurable learning rates, PPO clipping parameters, and checkpoint/logging infrastructure. Built on PyTorch with optional GPU acceleration via CUDA, plus real-time training visualization and a dedicated evaluation script.

243 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

243

Forks

51

Language

Python

License

MIT

Category

lunar-lander-rl

Last pushed

Nov 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/taherfattahi/ppo-rocket-landing"

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