[Feature] Added OpenEnv environments

[ParamThakkar123]

Description

Describe your changes in detail.

This PR adds OpenEnv environments to torchrl

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/3470

• 📄 Preview Python docs built from this PR

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

❌ 5 New Failures, 1 Unrelated Failure

As of commit dfaa211 with merge base 8038188 ():

NEW FAILURES - The following jobs have failed:

• Libs Tests on Linux / unittests-openenv (3.10, 12.8) / linux-job (gh)
  RuntimeError: Command docker exec -t 6d57732d51ddd2efbab72995516c1245a811b22dcd5f2645bf56893747c49160 /exec failed with exit code 4
• Lint / lint-done (gh)
  Process completed with exit code 1.
• Lint / python-source-and-configs / linux-job (gh)
• Unit-tests on Linux / tests-cpu (3.13) / linux-job (gh)
  test/objectives/test_ddpg.py::TestTD3::test_td3_prioritized_weights
• Unit-tests on Linux / tests-cpu (3.14) / linux-job (gh)
  test/objectives/test_ddpg.py::TestDDPG::test_ddpg_prioritized_weights

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

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

• LLM Tests on Linux / unittests-vllm (3.12, 12.9) / linux-job (gh) (trunk failure)
  test/llm/test_wrapper.py::TestLogProbsComparison::test_log_probs_consistency[unpadded-tokens]

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

[vmoens]

Awesome that you're working on this!
Would it make sense to use chatenv as a base class for consistency? No idea if that makes sense

[ParamThakkar123]

@vmoens I updated my code to use ChatEnv as a base class for OpenEnv

[vmoens]

See my comments below

[vmoens]

Almost every interaction with the underlying OpenEnv client is wrapped in bare try/except. This is very bad practice. In general we make everything we can in torchrl to avoid try/except entirely because it can quickly deteriorate UX and performance.

[vmoens]

are the import changes necessary? Circular imports I imagine

[ParamThakkar123]

yeah. Fixed that

[ParamThakkar123]

I am getting this error while importing it using from torchrl.envs import StepCounter, Transform:

ImportError while importing test module 'E:\rl\test\test_libs.py'.
Hint: make sure your test modules/packages have valid Python names.
Traceback:
E:\Miniconda3\Lib\importlib\__init__.py:88: in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
test\test_libs.py:15: in <module>
    import torchrl.testing.env_helper
torchrl\testing\__init__.py:17: in <module>
    from torchrl.testing.env_creators import (
torchrl\testing\env_creators.py:12: in <module>
    from torchrl.envs import MultiThreadedEnv, ObservationNorm
torchrl\envs\__init__.py:7: in <module>
    from .batched_envs import ParallelEnv, SerialEnv
torchrl\envs\batched_envs.py:3156: in <module>
    from torchrl.envs.libs.envpool import (  # noqa: F401, E402
torchrl\envs\libs\__init__.py:23: in <module>
    from .openenv import OpenEnvEnv, OpenEnvWrapper
torchrl\envs\libs\openenv.py:14: in <module>
    from torchrl.envs.llm.chat import ChatEnv
torchrl\envs\llm\__init__.py:7: in <module>
    from .datasets import (
torchrl\envs\llm\datasets\__init__.py:7: in <module>
    from .gsm8k import GSM8KEnv, GSM8KPrepareQuestion, make_gsm8k_env
torchrl\envs\llm\datasets\gsm8k.py:17: in <module>
    from torchrl.envs import StepCounter, Transform
E   ImportError: cannot import name 'StepCounter' from partially initialized module 'torchrl.envs' (most likely due to a circular import) (E:\rl\torchrl\envs\__init__.py)

So I changed the imports

[vmoens]

why this reorder?

[theap06]

@ParamThakkar123 I think we still have a circular import issue. lmk if you want any help with the pr!

[ParamThakkar123]

Thanks for the review @theap06 , I fixed the circular import issues and all the merge conflicts as well, lmk if there's any more changes we can make to this!