Skip to content

A Typo in the Definition of the Q-function in SAC Part? #355

@Gariscat

Description

@Gariscat

Hi! I am wondering whether there is a small typo in the definition of Q^{\pi}(s, a) in the soft actor-critic section. Shouldn't the second summation (the entropy part) start from "t=0" instead of "t=1"? Thanks a lot if you can check that!

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