Update VecNormalize normalization #609
Merged
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
Note that after the _update_rews() refactor, self.ret doesn't update anymore if `not self.training`.
|
Thanks for the PR, I'll try to do a review before next week ;) |
AdamGleave
requested changes
Dec 14, 2019
AdamGleave
reviewed
Dec 14, 2019
araffin
reviewed
Dec 15, 2019
AdamGleave
reviewed
Dec 15, 2019
Co-Authored-By: Adam Gleave <adam@gleave.me>
|
Thanks for the reviews! |
AdamGleave
reviewed
Dec 17, 2019
|
i dont have a strong opinion for your two comments |
shwang
added a commit
to HumanCompatibleAI/imitation
that referenced
this pull request
Dec 19, 2019
shwang
added a commit
to HumanCompatibleAI/imitation
that referenced
this pull request
Dec 20, 2019
* Fix errors due to SB change hill-a/stable-baselines#609 * normalize_{observation=>obs} * setup.py: Bump update note
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Outdated suggestions cannot be applied.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.
Description
Decouples normalization from mean/stddev tracking functionality.
Exposes reward and observation normalization for use outside of
.step()andreset().Add
get_original_rews()function which returns the most recent unnormalized rewards.reset()now updates statistics for observations in addition to normalizing.Motivation and Context
closes #602.
Types of changes
Checklist:
pytestandpytypeboth pass.