[RLlib] Add addtional_update to RL Trainer #31541
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
Signed-off-by: Avnish <avnishnarayan@gmail.com>
avnishn
requested review from
sven1977,
gjoliver,
ArturNiederfahrenhorst,
smorad,
maxpumperla,
kouroshHakha and
krfricke
as code owners
kouroshHakha
reviewed
Jan 9, 2023
rllib/core/rl_trainer/rl_trainer.py
Outdated
| @@ -205,6 +205,14 @@ def update(self, batch: MultiAgentBatch) -> Mapping[str, Any]: | |||
| self.do_distributed_update(batch) | |||
| return self.compile_results(batch, fwd_out, loss, post_processed_gradients) | |||
|
|
|||
| def additional_update(self) -> Mapping[str, Any]: | |||
There was a problem hiding this comment.
should it not take in any parameters? like *args, **kwargs? what should be returned? also provide some more context on where this would get called?
There was a problem hiding this comment.
fair enough, I thought there wasn't a point to adding args kwargs here because users can just do whatever they want
There was a problem hiding this comment.
then it should be *args, **kwargs to make it explicit. But the returned value should have some explaination.
Signed-off-by: Avnish <avnishnarayan@gmail.com>
kouroshHakha
approved these changes
Jan 9, 2023
AmeerHajAli
pushed a commit
that referenced
this pull request
Jan 12, 2023
Signed-off-by: Avnish <avnishnarayan@gmail.com>
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Outdated suggestions cannot be applied.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.
Signed-off-by: Avnish avnishnarayan@gmail.com
Add the additional updates function to the RL-Trainer.
For example, it could be used to do a polyak averaging update
of a target network in off policy algorithms like SAC or DQN.
Why are these changes needed?
Related issue number
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.