Skip to content

Conversation

@markelsanz14
Copy link

I believe these are two minor bugs, although if this is the intended behavior I apologize for the unnecessary changes.

I believe the current implementation will also train the RSSM model during evaluation, when training=False is passed. I'm not sure if this is the intended behavior but it looks like a bug to me.
…th the string of the passed distribution.

Minor bug fix. dist does not exist at that location in the code. Using self._dist would make the code clear if an incorrect distribution is passed.
NotImplementedError on ActionDecoder uses a None variable. Replace wi…
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant