coax 0.1.13

Plug-n-play reinforcement learning with Gymnasium and JAX

coax

Plug-n-Play Reinforcement Learning in Python with Gymnasium (formerly OpenAI Gym) and JAX

For the full documentation, including many examples, go to https://coax.readthedocs.io/

Install

coax is built on top of JAX, but it doesn’t have an explicit dependence on the jax python package. The reason is that your version of jaxlib will depend on your CUDA version. To install without CUDA, simply run:

$ pip install jaxlib jax coax --upgrade

If you do require CUDA support, please check out the Installation Guide.

Getting Started

Have a look at the Getting Started page to train your first RL agent.

---