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.
Summary: Introduced a feature to visualize boundaries in dimension-limited environments by displaying a rectangle. This visualization is triggered when both x_semidim and y_semidim parameters are defined and have non-None values.
This addition enhances the usability of the simulator in dimension-limited scenarios by providing a clear visual cue for the environment's boundaries.
Changes Made:
[environment.py]: added code to render a rectangle based on the x_semidim and y_semidim parameters. The visualization will only appear when both parameters are defined and set to specific values.
Description:
Changes Made: