-
Notifications
You must be signed in to change notification settings - Fork 5.4k
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] Fixed 'rollout_fragment_length' in pong-example by setting it to 'auto'. #39552
[RLlib] Fixed 'rollout_fragment_length' in pong-example by setting it to 'auto'. #39552
Conversation
Signed-off-by: Simon Zehnder <simon.zehnder@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great! Thanks for the fix
Signed-off-by: Artur Niederfahrenhorst <attaismyname@googlemail.com>
8663b28
to
0a9b440
Compare
Signed-off-by: Simon Zehnder <simon.zehnder@gmail.com>
Signed-off-by: Simon Zehnder <simon.zehnder@gmail.com>
@ArturNiederfahrenhorst Looking at the failed tests I think that the test is running on the wrong cluster: it requests a GPU (in the YAML) but there is none. Shall we add |
Signed-off-by: Simon Zehnder <simon.zehnder@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. Thanks! :)
@sven1977 I was the one who added the test. The reason we stumbled across this issue was that we don't test this code today - the issue was raised by a user who read the docs. In fact, all of our fine-tuned examples listed under |
I agree that the non-gpu learning test is not a good place, but instead, there should be another place where we execute this test. After all, if we can't prove learning on it, it should not be referred to as a fine-tuned example |
I've opened an issue #39639 |
… to 'auto'. (ray-project#39552) Signed-off-by: Simon Zehnder <simon.zehnder@gmail.com>
… to 'auto'. (ray-project#39552) Signed-off-by: Victor <vctr.y.m@example.com>
Why are these changes needed?
Pong
example did not run due to arollout_fragment_length
that did not fit thetrain_batch_size
. By setting therollout_fragment_length
toauto
therollout_fragment_length
adapts to thetrain_batch_size
.Related issue number
Closes #38968
Checks
git commit -s
) in this PR.scripts/format.sh
to lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/
under thecorresponding
.rst
file.