[RLlib] Make the "tiny CNN" example RLModule run with APPO (by implementing TargetNetAPI)
#49825
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
simonsays1980
approved these changes
Jan 15, 2025
| embeddings = self._target_base_cnn_stack(obs) | ||
| logits = self._target_logits(embeddings) | ||
| return { | ||
| OLD_ACTION_DIST_LOGITS_KEY: torch.squeeze(logits, dim=[-1, -2]) |
There was a problem hiding this comment.
Why do we have this key? And why is it in the APPO algforithm only. Can this then run with a single-agent setup?
There was a problem hiding this comment.
Great point! This should probably not be algo-specific, either.
We should call it "TARGET_ACTION_DIST_INPUTS" to make it generic, and move it somewhere else (in the rl_module/apis folder).
Will change ...
…target_api_to_example_rlms
ruisearch42
pushed a commit
to ruisearch42/ray
that referenced
this pull request
Jan 17, 2025
…enting `TargetNetAPI`) (ray-project#49825)
anson627
pushed a commit
to anson627/ray
that referenced
this pull request
Jan 31, 2025
…enting `TargetNetAPI`) (ray-project#49825) Signed-off-by: Anson Qian <anson627@gmail.com>
srinathk10
pushed a commit
that referenced
this pull request
Feb 2, 2025
…enting `TargetNetAPI`) (#49825)
anyadontfly
pushed a commit
to anyadontfly/ray
that referenced
this pull request
Feb 13, 2025
…enting `TargetNetAPI`) (ray-project#49825) Signed-off-by: Puyuan Yao <williamyao034@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Outdated suggestions cannot be applied.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.
Make the "tiny CNN" example RLModule run with APPO (by implementing
TargetNetAPI)Why are these changes needed?
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.