IS weights for prioritized replay #29
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
|
Thank you very much. It looks good. |
egafni
pushed a commit
to egafni/muzero-general
that referenced
this pull request
Apr 15, 2021
IS weights for prioritized replay
EpicLiem
pushed a commit
to EpicLiem/muzero-general-chess-archive
that referenced
this pull request
Feb 4, 2023
IS weights for prioritized replay
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Outdated suggestions cannot be applied.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.
Hey,
I implemented the IS weights based on my understanding. In$N$ and $P(i)$ according to the total number of samples in buffer and game/position sampling probabilities (with parameter
replay_buffer.py, I calculatedself.PER_beta). Then I normalize weights by 1/ maxi wi after getting theweight_batch. During training, theweights_batchis multiplied by the loss of each data sample.