GitHub repo

proroklab/VectorizedMultiAgentSimulator

Python Tracked since 2022-05-12 Updated 2026-07-16 View source ↗

#679 of 783 by Stars among GitHub repos

587 Stars

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.

About

We have released BenchMARL, a benchmarking library where you can train VMAS tasks using TorchRL! Check out how easy it is to use it.

This repository contains the code for the Vectorized Multi-Agent Simulator (VMAS).

VMAS is a vectorized differentiable simulator designed for efficient MARL benchmarking. It is comprised of a fully-differentiable vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Scenario creation is made simple and modular to incentivize contributions. VMAS simulates agents and landmarks of different shapes and supports rotations, elastic collisions, joints, and custom gravity. Holonomic motion models are used for the agents to…

Excerpted from github.com/proroklab/VectorizedMultiAgentSimulator

Latest metrics

Stars 587 2026-07-16
Forks 112 2026-07-16
Commits 614 2026-07-16
Releases 25 2026-07-16
Watchers 7 2026-07-16
Open issues 7 2026-07-16
Open PRs 1 2026-07-16