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.

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

Implement the corrected Exp3 and Exp4 algorithms #17

Closed
Naereen opened this issue Dec 19, 2016 · 2 comments
Closed

Implement the corrected Exp3 and Exp4 algorithms #17

Naereen opened this issue Dec 19, 2016 · 2 comments
Assignees
@Naereen
Labels
new algo I have to implement a new algorithm! Yay!

Comments

@Naereen
Copy link
Member

Naereen commented Dec 19, 2016

  • bd3f825 we should divide by the proba p_t of selecting actions, not by the trusts
@Naereen Naereen added the new algo I have to implement a new algorithm! Yay! label Dec 20, 2016
@Naereen Naereen self-assigned this Dec 20, 2016
@Naereen
Copy link
Member Author

Naereen commented Jan 25, 2017

  • Done for Aggr (Exp4)
  • TODO for Softmax (Exp3)

Naereen added a commit that referenced this issue Jan 25, 2017
@Naereen
Trying but failing to solve #17 for Softmax (Exp3)
b5a4c5a
@Naereen
Copy link
Member Author

Naereen commented Jan 26, 2017

I don't know, and don't care, about how to do that for Exp3.

@Naereen Naereen closed this as completed Jan 26, 2017
@Naereen Naereen mentioned this issue May 10, 2018
Closed
8 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Naereen Naereen

Labels
new algo I have to implement a new algorithm! Yay!
Milestone
No milestone
Development

No branches or pull requests
1 participant
@Naereen