This repository has been archived by the owner on May 19, 2021. It is now read-only.
fix ddpg to support tensorflow 2 #18
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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
I noticed that ddpg.py was not fully functional. Specifically, when running with tensorflow 2.0.1, we get TypeError: len is not well defined for symbolic Tensors. (activation_3/Identity:0) Please call
x.shaperather thanlen(x)for shape information. Based on #9 regarding removing shape assertions for dqn.py, I removed the shape assertions for ddpg.py as well. Next, I removed mentions of 'uses_learning_phase' attribute of Keras layers as this attribute does not seem to exist (see #16). I also disabled eager execution. Whilst this would not be ideal in regular implementations using Tensorflow 2.0, I noticed that it is implicitly disabled within compile() in dqn.py as well (by running tf.executing_eagerly() within the function) and figured it would not do much harm here.These fixes should make ddpg.py fully functional (as tested on ddpg_pendulum.py).