This repository was archived by the owner on Apr 11, 2021. It is now read-only.

This repository was archived by the owner on Apr 11, 2021. It is now read-only.

Could not find how to handle the intermediate rewards using rollout. #6

Open

opened

on Nov 12, 2017

In the original paper, they used rollout to get the intermediate rewards during sequence generation, in this codes, it seems the generator only gets rewards when the whole sequence is generated. Could you explain which part of the code corresponds to the rollout ?

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

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests