New/custom RL algorithm

[cexu2]

How do I add a custom RL algorithm? is there a file I need to modify ? a class that I need to implement? Any documentation will be great! I am new to gym and ray/rllib.

[fruffy]

Iroko is basically just a wrapper around OpenAI gym. To try out a new RL algorithm you would interface the same way as you would with the Gym environment. For example: https://github.com/dcgym/iroko/blob/master/run_basic.py is a basic test. https://github.com/dcgym/iroko/blob/master/run_ray.py interfaces with the Ray framework.

Keep in mind that this code is severely out of date.