Use num_batch_dims=0 to deal with observations containing scalars #231
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
When a (nested) observation contain a scalar value on some axes with dimension 1, batch_concat() will crash due to a shape mismatch error (e.g., cannot concatenate tensors of shape [100, 1] and []). This happens because batch_concat by default assumes the input tensors are batched, but when computing the statistics the batch dimensions (axis=0) already have been eliminated.
|
One additional favor: please rebase(squash) when merging, rather than creating a merge commit. |
qstanczyk
approved these changes
Jul 5, 2022
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Outdated suggestions cannot be applied.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.
When a (nested) observation contain a scalar value on some axes
with dimension 1, batch_concat() will crash due to a shape mismatch
error (e.g., cannot concatenate tensors of shape [100, 1] and []).
This happens because batch_concat by default assumes the input
tensors are batched, but when computing the statistics
the batch dimensions (axis=0) already have been eliminated.
Note: This applies to SAC agent. PPO agent already has a correct implementation (comparison here).