[BugFix, Feature] GNN position_key and velocity_key not in observation_spec
#125
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
facebook-github-bot
added
the
CLA Signed
Closed
matteobettini
changed the title
position_key and velocity_keyposition_key and velocity_key not in observation_spec
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Outdated suggestions cannot be applied.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 #124
Previously
GNN
position_keyandvelocity_keyneeded to be part of theobservation_specThis meant that they could not be used in a squence model where the GNN is not first as they would be accidentally consumed by other models
Now
Now these keys don't need to be in
observation_spec.In fact, it is better that they are not to solve the problem above.
They can be put in the info.
We still support the case of them being in
observation_specfor bc-compatibilityThe catch
Since now we do not know the shape of these keys (as they are not in the spec) we need to provide it in the model configuration. This is because GNNs need to know the shape of edge_features at init time.