VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning

by   Matteo Bettini, et al.

While many multi-robot coordination problems can be solved optimally by exact algorithms, solutions are often not scalable in the number of robots. Multi-Agent Reinforcement Learning (MARL) is gaining increasing attention in the robotics community as a promising solution to tackle such problems. Nevertheless, we still lack the tools that allow us to quickly and efficiently find solutions to large-scale collective learning tasks. In this work, we introduce the Vectorized Multi-Agent Simulator (VMAS). VMAS is an open-source framework designed for efficient MARL benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of twelve challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface. We demonstrate how vectorization enables parallel simulation on accelerated hardware without added complexity. When comparing VMAS to OpenAI MPE, we show how MPE's execution time increases linearly in the number of simulations while VMAS is able to execute 30,000 parallel simulations in under 10s, proving more than 100x faster. Using VMAS's RLlib interface, we benchmark our multi-robot scenarios using various Proximal Policy Optimization (PPO)-based MARL algorithms. VMAS's scenarios prove challenging in orthogonal ways for state-of-the-art MARL algorithms. The VMAS framework is available at https://github.com/proroklab/VectorizedMultiAgentSimulator. A video of VMAS scenarios and experiments is available at https://youtu.be/aaDRYfiesAY.


page 1

page 2

page 3

page 4


An Empirical Study on Google Research Football Multi-agent Scenarios

Few multi-agent reinforcement learning (MARL) research on Google Researc...

RIIT: Rethinking the Importance of Implementation Tricks in Multi-Agent Reinforcement Learning

In recent years, Multi-Agent Reinforcement Learning (MARL) has revolutio...

ROS-NetSim: A Framework for the Integration of Robotic and Network Simulators

Multi-agent systems play an important role in modern robotics. Due to th...

From Multi-agent to Multi-robot: A Scalable Training and Evaluation Platform for Multi-robot Reinforcement Learning

Multi-agent reinforcement learning (MARL) has been gaining extensive att...

Learning to Fly – a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control

Robotic simulators are crucial for academic research and education as we...

Contribution à l'Optimisation d'un Comportement Collectif pour un Groupe de Robots Autonomes

This thesis studies the domain of collective robotics, and more particul...

MARBLER: An Open Platform for Standarized Evaluation of Multi-Robot Reinforcement Learning Algorithms

Multi-agent reinforcement learning (MARL) has enjoyed significant recent...

Please sign up or login with your details

Forgot password? Click here to reset