[RLlib] - Enable multi-learner setup for hybrid stack BC #46436
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
…i-learner setups in BC impossible on the hybrid stack. Signed-off-by: simonsays1980 <[email protected]>
simonsays1980
added
rllib
sven1977
approved these changes
Jul 4, 2024
… and added logic in BC to add the used module ID if existent. Signed-off-by: simonsays1980 <[email protected]>
sven1977
reviewed
Jul 8, 2024
rllib/algorithms/bc/bc.py
Outdated
| train_results = self.learner_group.update_from_batch( | ||
| batch=train_batch.as_multi_agent( | ||
| module_id=list(self.config.policies)[0] | ||
| if self.config.policies |
There was a problem hiding this comment.
self.config.policies should always be available and you should always be able to iterate through it. So I don't think, we need this if-check here.
sven1977
reviewed
Jul 8, 2024
| @@ -147,6 +147,7 @@ | |||
| TRAINING_ITERATION: args.stop_iters, | |||
| } | |||
|
|
|||
| args.local_mode = True | |||
sven1977
reviewed
Jul 8, 2024
| @@ -907,14 +908,20 @@ def get(self, key, default=None): | |||
| return default | |||
|
|
|||
| @PublicAPI | |||
| def as_multi_agent(self) -> "MultiAgentBatch": | |||
| """Returns the respective MultiAgentBatch using DEFAULT_POLICY_ID. | |||
| def as_multi_agent(self, module_id: Optional[ModuleID] = None) -> "MultiAgentBatch": | |||
…able and removed local mode from example which is a relict from debugging. Signed-off-by: simonsays1980 <[email protected]>
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Outdated suggestions cannot be applied.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.
Why are these changes needed?
This PR does fix a bug in hybrid stack BC which was hindering multi-learner setups for offline RL.
Related issue number
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/under thecorresponding
.rstfile.