[bug-fix] Use correct memories for LSTM SAC #5228
Merged
Conversation
This file contains hidden or 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
andrewcoh
reviewed
Apr 7, 2021
andrewcoh
approved these changes
Apr 8, 2021
ervteng
pushed a commit
that referenced
this pull request
Apr 8, 2021
* Use correct memories for LSTM SAC * Add some comments (cherry picked from commit 7077302)
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Outdated suggestions cannot be applied.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.
Proposed change(s)
Use the right memories for SAC. Now that we are padding in the right direction, LSTM is much more sensitive to getting the memories right. Since SAC needs both the memory and the next memory (for the target network), we have to evaluate the next memory to get it.
Before, from 4/6 CI run (pink) and after (grey)
Useful links (Github issues, JIRA tickets, ML-Agents forum threads etc.)
Types of change(s)
Checklist
Other comments