BTgym have two main sections, the Gym framework and the RL algorithm framework.
The RL part is tailored to the unique gym requirements of BTgym, but as new research in the field is emerging there will be a benefit in exploring new algorithms that aren't implemented by this project.

The following tutorial is my own attempt of testing the integration between the Gym part of BTgym with an externa

From GCP tutorial

1. [bug] The tutorial references an old release

wget https://storage.googleapis.com/obstacle-tower-build/v1/obstacletower_v1_linux.zip
unzip obstacletower_v1_linux.zip

should be

wget https://storage.googleapis.com/obstacle-tower-build/v1.1/obstacletower_v1.1_lin

To be fixed by either

• Implementing own DDPG algo in examples folder
• Use a different neural network framework than keras-rl2
• update setup.py to keras_rl2 and annotate readme in examples on how to apply fixes to keras-rl2

RLLib (https://ray.readthedocs.io/en/latest/rllib.html) supports quite a lot of different algorithms and environments. And as it is built on top of ray it even scales to clusters.

I guess it should be quite straight forward to add support for it, as it integrates easily with OpenAI based environments (and even others too: https://ray.readthedocs.io/en/latest/rllib-env.html)