Make RecurrentRolloutBuffer generic to observations and states #8
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
dan-pandori
reviewed
Oct 10, 2023
This reverts commit 61cae13.
rhaps0dy
force-pushed
the
pytree-dataclass
branch
2 times, most recently
from
f98816a
to
1e7cf77
Compare
This was referenced Oct 13, 2023
Merged
rhaps0dy
added a commit
that referenced
this pull request
Oct 13, 2023
rhaps0dy
added a commit
that referenced
this pull request
Oct 13, 2023
Re-submission of #8 with all dependent PRs.
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Outdated suggestions cannot be applied.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.
There used to be a different class for Dict observations, and tensor observations; as well as the buffer only supported LSTM states.
Now there's a single class, and the state is generic.
This could potentially replace the non-recurrent buffers in
common/buffers.py, by using ahidden_state_example=(). However, those buffers don't need to do time padding, so the code is otherwise still different.Also:
--keep-goingoption to Pytype so it reports all type errors in a batch.