Wadaboa/flatland-challenge

Multi-agent reinforcement learning on trains, for Deep Learning class at UNIBO

25
/ 100
Experimental

This project provides solutions for optimizing train movements in a simulated railway network. It takes in railway network configurations and train movement rules, and outputs trained models that can efficiently manage multiple trains to reach their destinations with minimal delays and deadlocks. It's designed for researchers and students working on multi-agent reinforcement learning challenges in logistics and transportation.

No commits in the last 6 months.

Use this if you are a researcher or student looking for implementations and approaches to solve multi-agent reinforcement learning problems, specifically in the context of railway traffic management.

Not ideal if you're looking for a ready-to-use application to manage a real-world train system or if you're not familiar with Python, deep learning frameworks like PyTorch, and reinforcement learning concepts.

railway-optimization traffic-management logistics-simulation multi-agent-systems reinforcement-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

21

Forks

3

Language

TeX

License

Last pushed

Jan 14, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Wadaboa/flatland-challenge"

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