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

Supports elastic collisions, joints, custom gravity, and sensor simulation including LIDARs and inter-agent communication across diverse agent/landmark shapes. PyTorch vectorization enables batched parallel simulation scaling to tens of thousands of environments on GPU hardware. Provides Gym/Gymnasium-compatible interfaces with native integration into RLlib, TorchRL, and BenchMARL for end-to-end MARL training workflows.

531 stars.

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.