Skip to content
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

[RLlib] Issue 42396: Fix Algorithm.training_step() default implementation (multi-agent ALL_MODULES key causing error). #43316

Conversation

sven1977
Copy link
Contributor

@sven1977 sven1977 commented Feb 21, 2024

Issue 42396: Fix Algorithm.training_step() default implementation (multi-agent ALL_MODULES key causing error).

Why are these changes needed?

Closes #42396

Related issue number

Checks

  • I've signed off every commit(by using the -s flag, i.e., git commit -s) in this PR.
  • I've run scripts/format.sh to lint the changes in this PR.
  • I've included any doc changes needed for https://docs.ray.io/en/master/.
    • I've added any new APIs to the API Reference. For example, if I added a
      method in Tune, I've added it in doc/source/tune/api/ under the
      corresponding .rst file.
  • I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/
  • Testing Strategy
    • Unit tests
    • Release tests
    • This PR is not tested :(

Signed-off-by: sven1977 <svenmika1977@gmail.com>
Copy link

@garymm garymm left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the fix.
Would be nice for users if you tested this path too!

self.workers.sync_weights(
from_worker_or_learner_group=from_worker_or_trainer,
policies=list(train_results.keys()),
policies=set(train_results.keys()) - {ALL_MODULES},
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Crying out for a comment at least.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great catch @sven1977 !

Copy link
Collaborator

@simonsays1980 simonsays1980 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

self.workers.sync_weights(
from_worker_or_learner_group=from_worker_or_trainer,
policies=list(train_results.keys()),
policies=set(train_results.keys()) - {ALL_MODULES},
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great catch @sven1977 !

@sven1977 sven1977 merged commit 34876d8 into ray-project:master Feb 22, 2024
9 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[RLlib] Algorithm.training_step fails after episode termination because "__all__" is considered a module name
4 participants