AGI-Labs / continual_rl

Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.
MIT License
105 stars 11 forks source link

Integrate Rainbow Policy #13

Open tiencapham opened 4 months ago

tiencapham commented 4 months ago

Hi,

Thanks for your work on the framework, I found it very useful for research in CL.

Most of the current policies are based on Actor-Critic Framework. I think we can integrate the Q-Value learning such as Rainbow from this repo https://github.com/schmidtdominik/Rainbow.

I am not quite sure if it is trivial to do this integration.