[Feature] VIP Integration

[JasonMa2016]

Description

1. VIP model code in torchrl/transforms/vip.py.
2. Testing code appended to test/test_transforms.py.
3. Ensured that all tests pass.

Motivation and Context

New pre-trained visual encoder for RL from FAIR.

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.

[vmoens]

Thanks for this @JasonMa2016, wonderful contribution!
Do we want to design a reward transform while we're at it? Or should this be part of a separate PR?

[JasonMa2016]

Let's make reward transform a separate PR! We can discuss what's the best way to go about this.