christianhidber / easyagents

Reinforcement Learning for Practitioners.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Add support for RLLib

treo opened this issue · comments

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)

Great idea. Indeed it shouldn't be too difficult to integrate. Are you already using rllib ?

Yes, I've been using it for some previous projects.

I just looked into ray/rllib. It seems that windows is still not supported: ray-project/ray#2683 . At least pip install failed on Windows 10. That's a target platform of easyagents. :-(

As of ray 0.8.6 there is an experimental support for windows:
See:
ray-project/ray#631 (comment)
https://github.com/ray-project/ray/releases/tag/ray-0.8.6

Splendid, thanks for the hint. I'll definitely take a look at it.