[RLlib] Issue: Get single step input dict incorrect. #20217
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
…e_get_single_step_input_dict_incorrect
sven1977
added
the
tests-ok
gjoliver
reviewed
Nov 10, 2021
| }) | ||
| input_dict = batch.get_single_step_input_dict( | ||
| view_requirements=view_reqs, index="last") | ||
| check( |
There was a problem hiding this comment.
Our check() works on nested structures and also handles np.array vs list comparisons, so it's much more practical.
| }) | ||
| input_dict = batch.get_single_step_input_dict( | ||
| view_requirements=view_reqs, index="last") | ||
| check( |
| }) | ||
| input_dict = batch.get_single_step_input_dict( | ||
| view_requirements=view_reqs, index="last") | ||
| check( |
| }) | ||
| input_dict = batch.get_single_step_input_dict( | ||
| view_requirements=view_reqs, index="last") | ||
| check( |
| }) | ||
| input_dict = batch.get_single_step_input_dict( | ||
| view_requirements=view_reqs, index="last") | ||
| check( |
| def get_single_step_input_dict( | ||
| self, | ||
| view_requirements: ViewRequirementsDict, | ||
| index: Union[str, int] = "last", |
There was a problem hiding this comment.
it seems like index can be a tuple too. maybe update the annotation and doc string.
There was a problem hiding this comment.
I took out the Tuple option. Never used and doesn't seem to make any sense here.
We only ever use "last" or -1 (in the MARWIL algo).
| data = self[view_col][-1] | ||
| traj_len = len(self[data_col]) | ||
| missing_at_end = traj_len % view_req.batch_repeat_value | ||
| obs_shift = -1 if data_col in [ |
There was a problem hiding this comment.
can you help comment what obs_shift means?? I can't quite understand it. thanks.
gjoliver
approved these changes
Nov 11, 2021
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.
Fixes issue #20216
A new unit test has been added to the CI to cover this functionality in the future.
Why are these changes needed?
Related issue number
Checks
Closes #20216
scripts/format.shto lint the changes in this PR.