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.
simulator robotics simulation pytorch multi-agent gym vectorization multi-agent-systems vectorized multi-robot multi-robot-framework multi-agent-learning gym-environment multi-agent-simulation multi-agent-reinforcement-learning rllib marl multi-robot-simulator multi-robot-sim multi-robot-systems
-
Updated
Sep 30, 2025 - Python