tcbegley / rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[nanoChatGPT] Clean up config

tcbegley opened this issue · comments

ATM we have lots of options that are either redundant or not used, we should streamline and update the comments accordingly.

Example: dataset choice should be deprecated, as should model choice.

Single config for entire pipeline?