[RLlib] Fix IMPALA/APPO learning behavior: Fix EnvRunner sync bug, GPU loader thread, enable local learner w/ GPU. #48314
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]>
…joco 3.2…" This reverts commit d782b84.
Signed-off-by: sven1977 <[email protected]>
…impala_gpu_loader_thread_and_local_learner
… into fix_impala_gpu_loader_thread_and_local_learner
Signed-off-by: sven1977 <[email protected]>
sven1977
requested review from
a team,
maxpumperla,
simonsays1980,
richardliaw,
edoakes and
aslonnie
as code owners
sven1977
added
rllib
aslonnie
reviewed
Oct 29, 2024
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
…impala_gpu_loader_thread_and_local_learner
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
…impala_gpu_loader_thread_and_local_learner
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
…impala_gpu_loader_thread_and_local_learner
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
sven1977
requested review from
scottjlee,
bveeramani,
raulchen,
stephanie-wang,
omatthew98,
alexeykudinkin and
srinathk10
as code owners
Signed-off-by: sven1977 <[email protected]>
…accumulation_of_results_in_algorithm Signed-off-by: sven1977 <[email protected]> # Conflicts: # rllib/core/learner/tests/test_learner_group.py
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
Signed-off-by: sven1977 <[email protected]>
JP-sDEV
pushed a commit
to JP-sDEV/ray
that referenced
this pull request
Nov 14, 2024
…U loader thread, enable local learner w/ GPU. (ray-project#48314) Signed-off-by: JP-sDEV <[email protected]>
mohitjain2504
pushed a commit
to mohitjain2504/ray
that referenced
this pull request
Nov 15, 2024
…U loader thread, enable local learner w/ GPU. (ray-project#48314) Signed-off-by: mohitjain2504 <[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.
Enhance IMPALA/APPO learning behavior:
training_stepas IMPALA/APPO performs the Learner update, get weight-synched. All others (even though they also contributed to the train batch) stay behind, leading to a very large off-policyness.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.