-
Notifications
You must be signed in to change notification settings - Fork 4.2k
Fix DQN w RNN tutorial #3462
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
base: RC-TEST-2.8
Are you sure you want to change the base?
Fix DQN w RNN tutorial #3462
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/tutorials/3462
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit f4d1b1c with merge base 9a44439 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
@vmoens ^^ |
Resetting changes in favor of: #3462
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.
The decorator should be used when the policy is executed in the collector, not during instantiation of the policy object
policy = Seq(feature, lstm.set_recurrent_mode(True), mlp, qval) | ||
from torchrl.modules import set_recurrent_mode | ||
|
||
with set_recurrent_mode(True): |
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.
This is to be set during the loss computation.
The policy module given to the collector and to the loss will be the same. The decorator is to be set to True whenever a recurrent call is required (typically within the loss).
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.
Can you check the update, @vmoens ?
Thanks, @vmoens. I just attempted that. |
Fixes #3450
Fixes https://github.com/pytorch/tutorials/actions/runs/16273680500/job/45947334373?pr=3416#step:9:8137