[Feature] Add Dropout to MLP module #988
Merged
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Outdated suggestions cannot be applied.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.
Description
Adds the option to use dropout in the MLP layer module and changes the order when normalization classes are applied.
Motivation and Context
The option to add dropout to the MLP module wasn't there yet. I also changed the order of when normalization classes are applied. It is now done directly after the layer and before the activation function as done in the batch norm paper.
These changes open up the opportunity to create DroQ algorithm which is an improvement over REDQ and applies Dropout + LayerNorm in the Critic networks which makes it possible to have a high update-to-data ratio without the need of big ensemble sizes. Thus, DroQ is sample efficient as REDQ and computationally efficient as SAC which makes it very interesting for application in the real world e.g. robots.
Types of changes
What types of changes does your code introduce? Remove all that do not apply:
Checklist
Go over all the following points, and put an
x
in all the boxes that apply.If you are unsure about any of these, don't hesitate to ask. We are here to help!