Skip to content

Conversation

pilgrimygy
Copy link
Member

@findmyway
I finish a simple OfflinePolicy framework and we can use it to call the online algorithms by offline dataset.
I test the discrete CRR that has good performance.
But the continuous CRR is poor. I don't know why. I guess the actor_loss_coef calculation is wrong.

@pilgrimygy
Copy link
Member Author

And I test the Distributional Critic is inferior to normal Critic in performance.

@pilgrimygy pilgrimygy closed this Aug 5, 2021
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

Successfully merging this pull request may close these issues.

1 participant