[Doc] Fix/ppo tutorial

[coder-jayp]

Description

This PR updates the coding_ppo.py tutorial to explicitly separate the dummy forward pass (required to initialize LazyLinear modules) from the print statements. Additionally, a Sphinx .. note:: was added to clearly warn users that running the dummy batch is strictly required, preventing them from deleting this initialization logic when adapting the tutorial for their own scripts.

Motivation and Context

Users copying the tutorial code frequently removed the print() statements for the dummy forward passes, unaware that they served as the mandatory initialization step for the underlying LazyLinear parameters. This led to an UninitializedParameter error later in the PPO execution loop when attempting to disable gradients on the uninitialized modules. By explicitly separating the logic and warning the user, this UX bug is resolved.

Closes #3134

• 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:

• Documentation (update in the documentation)

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/4102

• 📄 Preview Python docs built from this PR

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

❌ 1 Unclassified Failure

As of commit dd0b68d with merge base 92a3f7f ():

UNCLASSIFIED FAILURE - DrCI could not classify the following job because the workflow did not run on the merge base. The failure may be pre-existing on trunk or introduced by this PR:

• Unit-tests on Linux / tests-cpu (3.10, bulk) / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  test/modules/test_multiagent_models.py::TestMultiAgent::test_multiagent_reset_mlp[False-False-3]

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

[github-actions]

⚠️ PR Title Label Error

PR title must start with a label prefix in brackets (e.g., [BugFix]).

Current title: Fix/ppo tutorial

Supported Prefixes (case-sensitive)

Your PR title must start with exactly one of these prefixes:

Prefix	Label Applied	Example
[Algorithm]	new algo	[Algorithm] Add new RL objective
[BE]	BE	[BE] Improve error messages
[Benchmark] or [Benchmarks]	Benchmarks	[Benchmark] Add collector benchmark
[BugFix]	BugFix	[BugFix] Fix memory leak in collector
[Example] or [Examples]	Examples	[Example] Add training script
[Feature]	Feature	[Feature] Add new optimizer
[Doc] or [Docs]	Documentation	[Doc] Update installation guide
[Refactor]	Refactoring	[Refactor] Clean up module imports
[CI]	CI	[CI] Fix workflow permissions
[Test] or [Tests]	Tests	[Tests] Add unit tests for buffer
[Trainer] or [Trainers]	Trainers	[Trainer] Add trainer config
[Environment] or [Environments]	Environments	[Environments] Add Gymnasium support
[Data]	Data	[Data] Fix replay buffer sampling
[LLM]	llm/	[LLM] Add reward model integration
[Minor]	small change	[Minor] Fix typo in error message
[Performance] or [Perf]	Performance	[Performance] Optimize tensor ops
[BC-Breaking]	bc breaking	[BC-Breaking] Remove deprecated API
[Deprecation]	Deprecation	[Deprecation] Mark old function
[Algorithm] or [Algorithms]	new algo	[Algorithm] Add new objective
[Quality]	Quality	[Quality] Fix typos and add codespell
[Versioning]	versioning	[Versioning] Bump release version
[WIP]	WIP	[WIP] Draft implementation

Note: Common variations like singular/plural are supported (e.g., [Doc] or [Docs]).

[vmoens]

I believe this branch is contaminated: Its description and issue link cover only coding_ppo.py, while the diff also adds PostTrainingLogger, rewrites GRPO/expert-iteration logging, changes accumulation boundaries, and adds 382 logger-test lines.

[github-actions]

⚠️ PR Title Label Error

PR title must start with a label prefix in brackets (e.g., [BugFix]).

Current title: Fix/ppo tutorial

Supported Prefixes (case-sensitive)

Your PR title must start with exactly one of these prefixes:

Prefix	Label Applied	Example
[Algorithm]	new algo	[Algorithm] Add new RL objective
[BE]	BE	[BE] Improve error messages
[Benchmark] or [Benchmarks]	Benchmarks	[Benchmark] Add collector benchmark
[BugFix]	BugFix	[BugFix] Fix memory leak in collector
[Example] or [Examples]	Examples	[Example] Add training script
[Feature]	Feature	[Feature] Add new optimizer
[Doc] or [Docs]	Documentation	[Doc] Update installation guide
[Refactor]	Refactoring	[Refactor] Clean up module imports
[CI]	CI	[CI] Fix workflow permissions
[Test] or [Tests]	Tests	[Tests] Add unit tests for buffer
[Trainer] or [Trainers]	Trainers	[Trainer] Add trainer config
[Environment] or [Environments]	Environments	[Environments] Add Gymnasium support
[Data]	Data	[Data] Fix replay buffer sampling
[LLM]	llm/	[LLM] Add reward model integration
[Minor]	small change	[Minor] Fix typo in error message
[Performance] or [Perf]	Performance	[Performance] Optimize tensor ops
[BC-Breaking]	bc breaking	[BC-Breaking] Remove deprecated API
[Deprecation]	Deprecation	[Deprecation] Mark old function
[Algorithm] or [Algorithms]	new algo	[Algorithm] Add new objective
[Quality]	Quality	[Quality] Fix typos and add codespell
[Versioning]	versioning	[Versioning] Bump release version
[WIP]	WIP	[WIP] Draft implementation

Note: Common variations like singular/plural are supported (e.g., [Doc] or [Docs]).

[vmoens]

Why? The prints in the next two lines do the exact same thing

[github-actions]

⚠️ PR Title Label Error

PR title must start with a label prefix in brackets (e.g., [BugFix]).

Current title: Fix/ppo tutorial

Supported Prefixes (case-sensitive)

Your PR title must start with exactly one of these prefixes:

Prefix	Label Applied	Example
[Algorithm]	new algo	[Algorithm] Add new RL objective
[BE]	BE	[BE] Improve error messages
[Benchmark] or [Benchmarks]	Benchmarks	[Benchmark] Add collector benchmark
[BugFix]	BugFix	[BugFix] Fix memory leak in collector
[Example] or [Examples]	Examples	[Example] Add training script
[Feature]	Feature	[Feature] Add new optimizer
[Doc] or [Docs]	Documentation	[Doc] Update installation guide
[Refactor]	Refactoring	[Refactor] Clean up module imports
[CI]	CI	[CI] Fix workflow permissions
[Test] or [Tests]	Tests	[Tests] Add unit tests for buffer
[Trainer] or [Trainers]	Trainers	[Trainer] Add trainer config
[Environment] or [Environments]	Environments	[Environments] Add Gymnasium support
[Data]	Data	[Data] Fix replay buffer sampling
[LLM]	llm/	[LLM] Add reward model integration
[Minor]	small change	[Minor] Fix typo in error message
[Performance] or [Perf]	Performance	[Performance] Optimize tensor ops
[BC-Breaking]	bc breaking	[BC-Breaking] Remove deprecated API
[Deprecation]	Deprecation	[Deprecation] Mark old function
[Algorithm] or [Algorithms]	new algo	[Algorithm] Add new objective
[Quality]	Quality	[Quality] Fix typos and add codespell
[Versioning]	versioning	[Versioning] Bump release version
[WIP]	WIP	[WIP] Draft implementation

Note: Common variations like singular/plural are supported (e.g., [Doc] or [Docs]).

[coder-jayp]

@vmoens Good catch. I wanted to prevent users from accidentally deleting the initialization if they remove the prints. I've just updated the PR to assign the outputs to variables instead, ensuring the forward pass only executes once.

[vmoens]

LGTM thanks!