[RLlib] IMPALA (any tf algo using entropy coeff) slowdown observed #15936
Labels
bug
Something that is supposed to be working; but isn't
P0
Issue that must be fixed in short order
release-blocker
P0 Issue that blocks the release
rllib
RLlib related issues
Since ray 1.2, IMPALA (and any other tf algorithm that uses
entropy_coeff
) has slowed down due to a bug.on_global_var_update
(defined inside theEntropyCoeffSchedule
(tf) mixin class).To reproduce:
rllib train -f rllib/tuned_examples/impala/pong-impala-fast.yaml
Runs much slower than in ray<=1.1.
What is the problem?
Ray version and other system information (Python version, TensorFlow version, OS):
Reproduction (REQUIRED)
Please provide a short code snippet (less than 50 lines if possible) that can be copy-pasted to reproduce the issue. The snippet should have no external library dependencies (i.e., use fake or mock data / environments):
If the code snippet cannot be run by itself, the issue will be closed with "needs-repro-script".
The text was updated successfully, but these errors were encountered: