Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

No comments in A2C code, very hard to read #285

Open
Kagaratsch opened this issue Feb 11, 2018 · 2 comments
Open

No comments in A2C code, very hard to read #285

Kagaratsch opened this issue Feb 11, 2018 · 2 comments

Comments

@Kagaratsch
Copy link

Kagaratsch commented Feb 11, 2018

Would it be possible to make the A2C code (and other algorithms) a bit more pedagogical?

@choinker
Copy link

choinker commented Feb 13, 2018

I agree some documentation would be nice, particularly with the output that is logged, can anyone explain what the output variables mean? Why (raw score / avg reward) over time isn't included?

@btaba
Copy link

btaba commented Mar 4, 2018

It looks like the raw env outputs are logged to a directory in /tmp created in monitor.py, which you can tail. It looks like they can be loaded after the fact with this.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants