Set TFPyEnv's reward shape per wrapped env's time_step_spec. #325
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
This allows environments to have non-scalar rewards. Relates to tensorflow#239.
ebrevdo
suggested changes
Mar 17, 2020
| @@ -333,7 +336,7 @@ def _set_names_and_shapes(self, step_type, reward, discount, | |||
| batch_shape = tf.TensorShape(batch_shape) | |||
| if not tf.executing_eagerly(): | |||
| # Shapes are not required in eager mode. | |||
| reward.set_shape(batch_shape) | |||
| reward.set_shape(batch_shape.concatenate(self._time_step_shapes[1])) | |||
There was a problem hiding this comment.
Why [1]? And why calculate all flattened shapes if you only use one of them?
There was a problem hiding this comment.
Hi @ebrevdo. Thanks for the feedback.
I agree, it is not as clear as it should be and not necessary to cache all shapes.. I've updated to not cache shapes in __init__ and to explicitly query self.time_step_spec().reward.shape rather than referring to it by its index position after flattening ([1]).
ebrevdo
approved these changes
Mar 18, 2020
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Outdated suggestions cannot be applied.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.
This allows environments to have non-scalar rewards.
Relates to #239.