[RLlib] Old API stack IMPALA/APPO: Re-introduce mixin-replay-buffer pass, even if replay-ratio=0 (fixes a memory leak).
#49964
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: sven1977 <[email protected]>
sven1977
added
rllib
simonsays1980
approved these changes
Jan 20, 2025
| replay_ratio=self.config.replay_ratio, | ||
| replay_mode=ReplayMode.LOCKSTEP, | ||
| ) | ||
| self.local_mixin_buffer = MixInMultiAgentReplayBuffer( |
There was a problem hiding this comment.
Dumb question: why do we even have a "mixin" replay buffer. Couldn't we just use a normal one and mix the batch in by ratio?
There was a problem hiding this comment.
see my answer below
| replay_ratio=self.config.replay_ratio, | ||
| replay_mode=ReplayMode.LOCKSTEP, | ||
| ) | ||
| self.local_mixin_buffer = MixInMultiAgentReplayBuffer( |
There was a problem hiding this comment.
Dumb question: why do we even have a "mixin" replay buffer. Couldn't we just use a normal one and mix the batch in by ratio?
There was a problem hiding this comment.
We could, but then again: This is old API stack. Not the time for any changes or experiments ;)
anson627
pushed a commit
to anson627/ray
that referenced
this pull request
Jan 31, 2025
…ass, even if `replay-ratio=0` (fixes a memory leak). (ray-project#49964) Signed-off-by: Anson Qian <[email protected]>
srinathk10
pushed a commit
that referenced
this pull request
Feb 2, 2025
…ass, even if `replay-ratio=0` (fixes a memory leak). (#49964)
jjyao
added a commit
to jjyao/ray
that referenced
this pull request
Feb 6, 2025
…buffer pass, even if `replay-ratio=0` (fixes a memory leak). (ray-project#49964)" This reverts commit 84b2b0e.
jjyao
added a commit
to jjyao/ray
that referenced
this pull request
Feb 11, 2025
…buffer pass, even if `replay-ratio=0` (fixes a memory leak). (ray-project#49964)" This reverts commit 84b2b0e.
8 tasks
jjyao
added a commit
that referenced
this pull request
Feb 12, 2025
Signed-off-by: Jiajun Yao <[email protected]>
anyadontfly
pushed a commit
to anyadontfly/ray
that referenced
this pull request
Feb 13, 2025
…ass, even if `replay-ratio=0` (fixes a memory leak). (ray-project#49964) Signed-off-by: Puyuan Yao <[email protected]>
israbbani
pushed a commit
that referenced
this pull request
Feb 25, 2025
Signed-off-by: Jiajun Yao <[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.
Old API stack IMPALA/APPO: Re-introduce mixin-replay-buffer pass, even if
replay-ratio=0(fixes a memory leak).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.