Just wonder the code does not have the entropy term in the PPO loss? #24

Open

opened

on Aug 25, 2025

The PPO equation should have the clipping term , entropy term and the value term?

So right now it only has the clipping term?

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