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

The mismatches between calls and implementations of some functions. #17

Open
Squirtle-gpj opened this issue Jul 25, 2022 · 1 comment
Open

Comments

@Squirtle-gpj
Copy link

Hello,

This benchmark is very nice. But when I want to use it, I find some confusing parts in the code.

For example, in line 221 of paper.py, the code is:

retrace = Retrace(behavior_data, gamma, lamb=.9, max_iters=50)
out0, Q, mapping = retrace.run(pi_b, pi_e, 'retrace', epsilon=.002)

However, in the implementation of the Retrace class (which is located at algos.retrace_lambda.py), the init function is:

def init(self, method, lamb) -> None:

and there is not a function called run in this class.

There are many similar mismatches in this benchmark (like other algo classes), so I want to know whether you could fix this problem.

Best Regards
Pengjie

@clvoloshin
Copy link
Owner

Please try paper.py on the paper branch. The current master branch has been nearly entirely refactored

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

2 participants