Mava

About

Mava allows researchers to experiment with multi-agent reinforcement learning (MARL) at lightning speed. The single-file JAX implementations are built for rapid research iteration - hack, modify, and test new ideas fast. Our [state-of-the-art algorithms][sable] scale seamlessly across devices. Created for researchers, by The Research Team at InstaDeep.

At the moment Mava is not meant to be installed as a library, but rather to be used as a research tool. We recommend cloning the Mava repo and installing dependencies using uv as follows:

To install Mava with a GPU or TPU aware version of JAX

Alternatively with pip, create a virtual environment and then:

We have tested Mava on Python 3.11…