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

Custom bandit rewards and policy network layers #1

Open

daniel-xion opened this issue Aug 29, 2022 · 0 comments

daniel-xion commented Aug 29, 2022 •

edited

Loading

Thanks for the code. I have two questions.

How to define custom bandits and their rewards, instead of using some predefined distribution?
The reward part looks like a policy network. Can we add a policy network with layers of neurons (MLP) into the model? How to do that exactly?
(sorry I'm quite new to this)

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