[Feature] Add reduction parameter to On-Policy losses.

[albertbou92]

Description

This PR introduces a reduction option to the on-policy losses, similar to how Torch does it (e.g. https://pytorch.org/docs/stable/generated/torch.nn.MSELoss.html).

The ideas is to validate the approach for on-policy losses, the then move on to replicate it in the other losses.

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.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1890

• 📄 Preview Python docs built from this PR

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

✅ You can merge normally! (5 Unrelated Failures)

As of commit 8052e33 with merge base 899af07 ():

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

• Continuous Benchmark (PR) / CPU Pytest benchmark (gh)
  Workflow failed! Resource not accessible by integration
• Continuous Benchmark (PR) / GPU Pytest benchmark (gh)
  Workflow failed! Resource not accessible by integration
• Habitat Tests on Linux / tests (3.9, 11.6) / linux-job (gh)
  RuntimeError: Command docker exec -t 3d397f92035cc11ee3d8f266d3c8dc389ec818a1447cde0555bb4b060913d5d2 /exec failed with exit code 139
• Unit-tests on MacOS CPU / tests (3.8) / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 1

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• Unit-tests on Windows / unittests-gpu / windows-job (gh)
  ##[error]The operation was canceled.

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

[vmoens]

Great stuff!
I wonder if long term we should not structure the loss better, to avoid the batch-size issue pointed here.

TensorDict({"loss": {"actor": tensor, ...}, "metadata": {...}}, [])

which could let us set a different batch-size at diferent levels.
It isn't going to be easy to move to that format though! So for now I think the best would be to keep the output without batch-size until we figure out how to account for it long-term.

[albertbou92]

I incorporated a part of the suggestions and left comments in the points that might need further discussion

[vmoens]

LGTM just smth minor in the tests