Skip to content

walker_stand critic loss explosion #26

@seolhokim

Description

@seolhokim

Hi, thank you for quality code. but I wonder why walker_stand task critic loss is too high(up to 1e+3) in my experiment. In my case, I used your conda.yaml and changed env :walker_stand and action_repeat : 2 and batch_size : 512 as you mentioned in paper. how can I get stable critic loss?(for example, reward scaling)

Thank you for reading.

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