proroklab/VectorizedMultiAgentSimulator

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

60
/ 100
Established

This tool helps robotics researchers and engineers test and benchmark multi-robot coordination strategies. It simulates various scenarios with multiple robots and obstacles, taking in control policies and outputting simulation results and performance metrics. It's designed for anyone working on multi-agent reinforcement learning for robot teams.

531 stars.

Use this if you need to efficiently simulate and train AI agents for complex multi-robot systems across many different scenarios.

Not ideal if you need a real-time, high-fidelity physics simulator for physical hardware deployment or single-robot control tasks.

multi-robot-systems robot-control reinforcement-learning robot-simulation multi-agent-AI
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

531

Forks

104

Language

Python

License

GPL-3.0

Last pushed

Feb 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/proroklab/VectorizedMultiAgentSimulator"

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