rlax: Upstream Muesli utilities to rlax. #113
Open
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
copybara-service
bot
force-pushed
the
test_493987878
branch
3 times, most recently
from
d8a2e74 to
fe8b3f5
Compare
We now provide methods for constructing the clipped MPO (CMPO) policy targets used as part of the Muesli agent loss. These CMPO targets are in expectation proportional to: `prior(a|s) * exp(clip(norm(Q(s, a))))` where the prior is computed by the actor policy head, and the Q values are computed using the learned model's reward and value heads. See "Muesli: Combining Improvements in Policy Optimization" by Hessel et al. (https://arxiv.org/pdf/2104.06159.pdf) for more details. PiperOrigin-RevId: 493987878
copybara-service
bot
force-pushed
the
test_493987878
branch
from
fe8b3f5 to
457da00
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
rlax: Upstream Muesli utilities to rlax.
We now provide methods for constructing the clipped MPO (CMPO) policy targets used as part of the Muesli agent loss. These CMPO targets are in expectation proportional to:
prior(a|s) * exp(clip(norm(Q(s, a))))where the prior is computed by the actor policy head, and the Q values are computed using the learned model's reward and value heads.See "Muesli: Combining Improvements in Policy Optimization" by Hessel et al. (https://arxiv.org/pdf/2104.06159.pdf) for more details.