Skip to content

Has anyone compared this training framework to TRL? #54

@StarrySeas1

Description

@StarrySeas1

TRL PPO implementation is simpler than this, and takes up less memory. This framework has an additional value contribution network. I don't know which framework is more stable and effective.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions