[Question] Would you like a pull request implementing classical tabular RL algorithms ?

[Butanium]

❓ Question

Hi,

I'm working on a variation of DQN. As I have some unexpected results, I want to make the same variation but on tabular Q Learning instead.

As sb3 doesn't have tabular implementation, I made my own. For now I didn't add test etc but I was wondering if you'd be interested in a pull request implementing such non-deep algorithm.

Let me know what you think!

Checklist

• I have checked that there is no similar issue in the repo
• I have read the documentation
• If code there is, it is minimal and working
• If code there is, it is formatted using the markdown code blocks for both code and stack traces.

[araffin]

related: DLR-RM/stable-baselines3#786 and DLR-RM/stable-baselines3#1384