-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
R2D2 #34
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
I think the key is doing a reversed loop for the n step returns rather than a vmap
to support setting priorities for replay
currently crashes with regular python, probably due to buffer donation bug, but runs with debug python not sure if it's working yet
does not appear to be learning cartpole, so something is wrong
add more tests test_r2d2_learns_cartpole currently fails
before it seems it was a no-op for some reason having to do with vmap
this matches the implementation in Acme
add learning rate schedule make number of optimizations per cycle configurable log hyperparameters
Main thing changed was shrinking replay buffer
The actor state being returned was sharded for a single learner device
shrink atari game for TPU memory savings
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #34 +/- ##
==========================================
- Coverage 96.74% 93.08% -3.67%
==========================================
Files 13 16 +3
Lines 1168 1750 +582
==========================================
+ Hits 1130 1629 +499
- Misses 38 121 +83 ☔ View full report in Codecov by Sentry. |
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Outdated suggestions cannot be applied.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.
R2D2 agent and the necessary changes to Earl to implement it.