Skip to content

clamp ratio #3

@cswhjiang

Description

@cswhjiang

It seems that you should clamp ratio, not surr1.

https://github.com/alexis-jacq/Pytorch-DPPO/blob/master/ppo.py#L145

Metadata

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

    Issue actions