VectorizedMultiAgentSimulator
VectorizedMultiAgentSimulator copied to clipboard
proroklab
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...
Hello, The ray example was super helpful in getting things up and running, however, when I tried to configure the PPOTrainer to use one policy per agent, the wrapper provided...
**Issue:** In scenarios where agents are equipped with Lidar, the "n_rays" parameter is currently fixed at 12. It would be beneficial to allow users to set this parameter via the...
**Issue:** In certain scenarios, users may work with environments that have limited dimensions, which can be configured using the "x_semidim" and "y_semidim" parameters. In such cases, it would be beneficial...
Hello, Thank you for this helpful repository! I’m trying to reproduce the results of experiments from one of your papers, [VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning](https://matteobettini.com/publication/vmas-a-vectorized-multi-agent-simulator-for-collective-robot-learning/), using...
