[BugFix] make sure the params of exploration-wrapper is float

[FrankTianTT]

Description

we should make sure the params of exploration-wrapper is float, or the params decay maybe abnormal.

Motivation and Context

If the user passes an int into the wrapper (e.g. "1" instead of "1.0", like stupid me), the params will always be 0 and don't change throughout the step is called:

 policy = TensorDictModule(
      module=torch.nn.Linear(4, 4, bias=False),
      in_keys="observation",
      out_keys="action",
  )
  p = OrnsteinUhlenbeckProcessWrapper(
      policy,
      eps_init=1,
  )
  for i in range(10):
      p.step()
      print(p.eps.item())

result is

0
0
0
0
0
0
0
0
0
0

if we pass a float, the function of wrapper is normal:

 policy = TensorDictModule(
      module=torch.nn.Linear(4, 4, bias=False),
      in_keys="observation",
      out_keys="action",
  )
  p = OrnsteinUhlenbeckProcessWrapper(
      policy,
      eps_init=1.0,
  )
  for i in range(10):
      p.step()
      print(p.eps.item())

result is

0.9991000294685364
0.9982000589370728
0.9973000884056091
0.9964001178741455
0.9955001473426819
0.9946001768112183
0.9937002062797546
0.992800235748291
0.9919002652168274
0.9910002946853638

the reason of this bug is we use the type of eps_init as the type of self.eps.

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/1700

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures, 6 Unrelated Failures

As of commit 09878b1 with merge base 0a38cbc ():

NEW FAILURES - The following jobs have failed:

• Build M1 Wheels / pytorch/rl / wheel-py3_8-cpu (gh)
• Examples Tests on Linux / tests (3.9, 12.1) / linux-job (gh)

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

• Continuous Benchmark (PR) / CPU Pytest benchmark (gh)
• Continuous Benchmark (PR) / GPU Pytest benchmark (linux.4xlarge.nvidia.gpu, 3.8) (gh)
• Unit-tests on MacOS CPU / tests (3.11) / macos-job (gh)

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

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

• Habitat Tests on Linux / tests (3.9, 11.6) / linux-job (gh)
• Unit-tests on Windows CPU / unittests / windows-job (gh)
• Unit-tests on Windows GPU / unittests / windows-job (gh)

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

[vmoens]

Fantastic thanks a million