skypitcher/risk_aware_marl

Risk-aware multi-agent deep reinforcement learning for packet routing in ultra-dense LEO satellite networks

25
/ 100
Experimental

This project helps satellite network operators manage packet routing in large, complex Low Earth Orbit (LEO) satellite constellations. It takes in real-time network conditions and traffic, then outputs optimized routing decisions that minimize network congestion and delays. The primary users are engineers and operations managers responsible for maintaining robust and efficient LEO satellite communication networks.

Use this if you need to simulate and optimize packet routing strategies for ultra-dense LEO satellite networks, especially to reduce network congestion and ensure reliable, low-latency data delivery.

Not ideal if you are managing traditional terrestrial networks or require a physical network deployment for immediate real-world operation rather than a simulation and optimization framework.

LEO-satellite-operations network-traffic-management telecommunications constellation-management packet-routing
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

MIT

Last pushed

Dec 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/skypitcher/risk_aware_marl"

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