Aug 6 changes #16
Closed
Aug 6 changes #16
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…use i literally just increased size of actor/critic models. maybe should do some ablation tests. or get working fully first! (better reward func)
Got nans in training and trying to fix by norm'ing obs and also adding epsilon to action_log_pdf. Also some cleaning
* added tricks from blogpost * reorder memory * shown trying to stand up + increasing score? not sure if this is because i literally just increased size of actor/critic models. maybe should do some ablation tests. or get working fully first! (better reward func)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Get nans in scores after close to standing up (when there are nans, the episode count is very long, meaning there's no failures --- pretty sure it's standing up). Nans makes it not possible to see recording + make it impossible to see further actor/critic convergence though, so unable to fully tell.
Probably an infra issue somewhere but Pawel's training some stuff right now so we'll maybe get to see later.