Skip to content
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

[BugFix,Refactor] Dreamer refactor #1918

Merged
merged 125 commits into from
Apr 23, 2024
Merged

Conversation

BY571
Copy link
Contributor

@BY571 BY571 commented Feb 16, 2024

Description

Updates the dreamer example to be aligned with other example scripts and prove paper performance.
Adds the option to run dreamer with non-image obs environments and fixes small issues in the objective and other elements.

Motivation and Context

Why is this change required? What problem does it solve?
If it fixes an open issue, please link to the issue here.
You can use the syntax close #15213 if this solves the issue #15213

  • I have raised an issue to propose this change (required for new features and bug fixes)

Types of changes

What types of changes does your code introduce? Remove all that do not apply:

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds core functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Documentation (update in the documentation)
  • Example (update in the folder of examples)

Checklist

Go over all the following points, and put an x in all the boxes that apply.
If you are unsure about any of these, don't hesitate to ask. We are here to help!

  • I have read the CONTRIBUTION guide (required)
  • My change requires a change to the documentation.
  • I have updated the tests accordingly (required for a bug fix or a new feature).
  • I have updated the documentation accordingly.

Copy link

pytorch-bot bot commented Feb 16, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1918

Note: Links to docs will display an error until the docs builds have been completed.

❌ 6 New Failures, 11 Unrelated Failures

As of commit 7733c37 with merge base 0ea236d (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Feb 16, 2024
@BY571
Copy link
Contributor Author

BY571 commented Feb 16, 2024

image

Current performance for cheetah run dm_control task. Not yet paper performance.

@@ -2421,6 +2421,10 @@ def _rollout_stop_early(
tensordict = tensordict.to(policy_device, non_blocking=True)
else:
tensordict.clear_device_()

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not ideal and just a current solution, Id be interested to hear what you think @vmoens. We need to detach those values similar to this maybe via a detach transform?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

do we need to backprop anything in this loop?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I added a transform to the mb env,
can you confirm that we always want to detach these values in mbenv.step?

@vmoens vmoens changed the title [WIP] Dreamer refactor [BugFix,Refactor] Dreamer refactor Apr 8, 2024
vmoens added 5 commits April 8, 2024 11:15
# Conflicts:
#	sota-implementations/dreamer/dreamer_utils.py
#	torchrl/objectives/dreamer.py
frames_per_batch=cfg.collector.frames_per_batch,
total_frames=cfg.collector.total_frames,
device=cfg.collector.device,
reset_at_each_iter=True,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We should set the horizon instead

Comment on lines +204 to +207
return (
-0.5 * ((x.to(mean.dtype) - mean) / std).pow(2) - std.log()
) # - 0.5 * math.log(2 * math.pi)

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

here's the equation of the normal log prob if you're interested. It's a distance loss as you can see

@vmoens vmoens marked this pull request as ready for review April 18, 2024 16:08
torchrl/objectives/dreamer.py Outdated Show resolved Hide resolved
torchrl/objectives/dreamer.py Outdated Show resolved Hide resolved
@vmoens vmoens merged commit bfadce9 into pytorch:main Apr 23, 2024
21 of 27 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants