T3AS/MAD-ARL

Python project for the paper "Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies".

35
/ 100
Emerging

This project helps autonomous driving engineers and researchers rigorously test the safety and robustness of multi-agent self-driving car policies. It simulates complex driving scenarios within the CARLA environment, allowing you to feed in your autonomous driving algorithms and assess how well they perform against adversarial conditions and other vehicles. The output provides insights into the vulnerabilities and strengths of these policies, which is critical for developing safer autonomous systems.

No commits in the last 6 months.

Use this if you need to evaluate and improve the resilience of multi-agent autonomous driving systems against diverse and challenging scenarios.

Not ideal if you are looking for a general-purpose driving simulator for entertainment or basic policy development, as its focus is on adversarial testing.

autonomous-driving robotics-testing vehicle-safety reinforcement-learning-evaluation multi-agent-systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

14

Forks

3

Language

Python

License

GPL-3.0

Last pushed

Feb 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/T3AS/MAD-ARL"

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