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.

Sign up for GitHub

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

Jump to bottom

np.argmax bias #3

Open

kvkpraneeth opened this issue Sep 24, 2020 · 0 comments

kvkpraneeth commented Sep 24, 2020 •

edited

Loading

The function np.argmax, does not cut ties randomly:

eg:
Q = [1,0,1]
np.argmax always picks the first 1.

Whereas all ties while selecting should be cut randomly. This can lead to action bias.

np.argmax was used in bandit.py in chapter 2 folder.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment