trlx
trlx copied to clipboard
CarperAI
How we can improve the documentation for beginners
📚 The doc issue
Hey there 👋 I've done a first review of the documentation.
For context, I've skimmed the documentation as a beginner to see where are the friction points.
I've some solutions for some, that's why I opened a PR: #64
For others I prefer for now to open an issue to discuss with you on how we can improve it.
So here's the points:
- The documentation is clear and very well written. I think though we need to explain more how TRLX works in a nutshell. For instance, Leandro in TRL have a section where he made very good illustration to explain how it works https://github.com/lvwerra/trl/#how-it-works
-
For the example page I was thinking on a readme explaining each different example (and update the website documentation)
-
A simple colab as a quick starter can be interesting to have. For instance for SB3 integration we created a small one where in 10min you trained your first agent and load a PPO agent from the Hub to play Space Invaders. Having that kind of quick run colab can help people to rapidly get the big picture of the library.
-
We miss a Bibtex for citing.
WDYT? 🤔
Suggest a potential alternative/fix
PR: https://github.com/CarperAI/trlx/pull/64
@simoninithomas This looks great, as I mentioned in the TRLX weekly I'd love to help out creating quick-start colab notebooks. Do you have any vision in mind, or should I just give it a shot and put up a PR for review?
@thedch I don't have for now a vision in mind. I was thinking on a quickstart with a simple model that we can train and test. If you have some ideas open a new PR so that we can exchange on it 🤗
Is there any support group for trlx.. saw some comments for trlx weekly meeting?
TRLX weekly is Monday at 1pm est in the discord. It's more of an engineering standup meeting than office hours. We've done office hours in the past though, let me know if this is something that interests you :)