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.
It is also a really good place to find something you would like to contribute.
Features
[ ] Reset any number of dimensions (#73) (basically we now can reset either one env or all of them, it would be nice to reset with any tyope of index) (this is highly laboruous as it requires adapting all scenarios, maybe take it one scenario at a time)
[x] Check kwargs in scenarios (#114)(#117) (scenarios need to consume kwargs instead of reading them and then we can check if all have been consumed)
Hello people!
In this issue I will list the things I would really like to have in VMAS and will tick them off as they are implemented!
These were previously in the README TODOs
It is also a really good place to find something you would like to contribute.
Features
Sensors