Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
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.
| Date | Stars |
|---|---|
| 2026-07-25 | 589 |
| 2026-07-28 | 589 |
| 2026-07-30 | 589 |
| 2026-07-31 | 594 |
| 2026-08-02 | 595 |
| 2026-08-05 | 595 |
| 2026-08-07 | 595 |
| 2026-08-08 | 595 |
| 2026-08-09 | 596 |
| 2026-08-11 | 597 |
| 2026-08-14 | 598 |
| 2026-08-15 | 599 |
| 2026-08-16 | 599 |
| 2026-08-18 | 599 |
| 2026-08-21 | 598 |
| 2026-08-23 | 599 |
| 2026-08-24 | 601 |
| 2026-08-29 | 602 |
| 2026-09-02 | 603 |
| 2026-09-04 | 604 |
| 2026-09-12 | 605 |
| 2026-09-13 | 606 |
| 2026-09-15 | 607 |
| 2026-09-16 | 608 |
| 2026-09-17 | 609 |
| 2026-09-18 | 610 |
| 2026-09-20 | 610 |
Today
— stars today
This week
+4 stars this week
This month
+12 stars this month
Momentum
0.0
growth rate 0.66%/day
# VectorizedMultiAgentSimulator (VMAS)
<a href="https://pypi.org/project/vmas"><img src="https://img.shields.io/pypi/v/vmas" alt="pypi version"></a>
[](https://pepy.tech/project/vmas)
[](https://codecov.io/gh/proroklab/VectorizedMultiAgentSimulator)
[](https://vmas.readthedocs.io/en/latest/?badge=latest)
[](https://www.python.org/downloads/)
[](https://github.com/proroklab/VectorizedMultiAgentSimulator/blob/main/LICENSE)
[](https://arxiv.org/abs/2207.03530)
[](https://discord.gg/dg8txxDW5t)
[](https://colab.research.google.com/github/proroklab/VectorizedMultiAgentSimulator/blob/main/notebooks/Simulation_and_training_in_VMAS_and_BenchMARL.ipynb)
<p align="center">
<img src="https://github.com/matteobettini/vmas-media/blob/main/media/VMAS_scenarios.gif?raw=true" alt="drawing"/>
</p>
> [!NOTE]
> We have released [BenchMARL](https://github.com/facebookresearch/BenchMARL), a benchmarking library where you
> can train VMAS tasks using TorchRL!
> Check out [how easy it is to use it.](https://colab.research.google.com/github/facebookresearch/BenchMARL/blob/main/notebooks/run.ipynb)
## Welcome to VMAS!
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 simplify simulation. Custom sensors such as LIDARs are available and the simulator supports inter-agent communication.
Vectorization in [PyTorch](https://pytorch.org/) allows VMAS to perform simulations in a batch, seamlessly scaling to tens of thousands of parallel environments on accelerated hardware.
VMAS has an interface compatible with [OpenAI Gym](https://github.com/openai/gym), with [Gymnasium](https://gymnasium.farama.org/), with [RLlib](https://docs.ray.io/en/latest/rllib/index.html), with [torchrl](https://github.com/pytorch/rl) and its MARL training library: [BenchMARL](https://github.com/facebookresearch/BenchMARL),
enabling out-of-the-box integration with a wide range of RL algorithms.
The implementation is inspired by [OpenAI's MPE](https://github.com/openai/multiagent-particle-envs).
Alongside VMAS's scenarios, we port and vectorize all the scenarios in MPE.
### [Paper](https://arxiv.org/abs/2207.03530)
The arXiv paper can be found [here](https://arxiv.org/abs/2207.03530).
If you use VMAS in your research, **cite** it using:
```
@article{bettini2022vmas,
title = {VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning},
author = {Bettini, Matteo and Kortvelesy, Ryan and Blumenkamp, Jan and Prorok, Amanda},
year = {2022},
journal={The 16th International Symposium on Distributed Autonomous Robotic Systems},
publisher={Springer}
}
```
### Video
Watch the presentation video of VMAS, showing its structurExcerpt of 76,417 characters
Read on GitHub
Matteo Bettini · Meta
497
61
35
4
3
2
2
1
1
1
1
Abhishek
1
1
1
1
Ikko Eltociear Ashimine · Japan
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ae5b0f6cae5945b3, topic:multi-agent, topic:multi-agent-systems, desc:multi-agent
matched fp:ae5b0f6cae5945b3, topic:multi-agent-reinforcement-learning, desc:reinforcement learning, readme:rl algorithms
matched fp:ae5b0f6cae5945b3, topic:robotics, topic:simulation, readme:robot learning