[Tests] add recurrent integration coverage

[theap06]

Fixes #3746

Summary

Adds a focused integration test for recurrent state handling across trajectory boundaries. The test exercises an LSTM policy with SyncDataCollector on a deterministic environment that terminates mid-batch, verifies is_init propagation, and confirms that recurrent hidden state does not leak across trajectories after the replay-buffer / recurrent-loss-side path.

Complements #3792 (the docs and rnn.py docstring portion of the recurrent-state lifecycle work) with the missing integration-level coverage. Unit-level recurrent paths are already covered in test/modules/test_rnn.py; value-function-side recurrent coverage lives in test/objectives/test_values.py::TestValues::test_gae_recurrent. Neither exercises the full policy → collector → buffer integration this PR fills.

Notes

• SyncDataCollector is deprecated as of v0.13 in favor of Collector. This PR uses SyncDataCollector to match the wording of the original issue; a trivial follow-up swaps the import when the deprecation lands.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/3793

• 📄 Preview Python docs built from this PR

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

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: add recurrent integration coverage

Supported Prefixes (case-sensitive)

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

Prefix	Label Applied	Example
[BugFix]	BugFix	[BugFix] Fix memory leak in collector
[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
[Environment] or [Environments]	Environments	[Environments] Add Gymnasium support
[Data]	Data	[Data] Fix replay buffer sampling
[Performance] or [Perf]	Performance	[Performance] Optimize tensor ops
[BC-Breaking]	bc breaking	[BC-Breaking] Remove deprecated API
[Deprecation]	Deprecation	[Deprecation] Mark old function
[Quality]	Quality	[Quality] Fix typos and add codespell

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

[theap06]

@vmoens feel free to leave some feedback when ur free. also lmk if there is anything I can do to help with general maintainance of the library

[vmoens]

LGTM
Moved to an existing file