[Feature] Extend PPO loss helper to allow for more customisation

[albertbou92]

Description

The helper function that creates the PPO loss does not allow specifying things like the clipping parameter for the ClipPPOLoss version of the loss, the KL coefficient for KLPENPPOLoss, etc.

This PR suggest minor changes to allow for this customisation.

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.

[codecov]

Codecov Report

Merging #718 (535c2bd) into main (bac229a) will decrease coverage by 0.03%.
The diff coverage is 60.00%.

@@            Coverage Diff             @@
##             main     #718      +/-   ##
==========================================
- Coverage   88.66%   88.63%   -0.04%     
==========================================
  Files         120      120              
  Lines       20186    20200      +14     
==========================================
+ Hits        17898    17904       +6     
- Misses       2288     2296       +8     

Flag	Coverage Δ
habitat-gpu	25.05% <ø> (ø)
linux-cpu	85.57% <60.00%> (-0.02%)	⬇️
linux-gpu	86.52% <60.00%> (-0.02%)	⬇️
linux-jumanji	30.27% <ø> (ø)
linux-outdeps-gpu	72.21% <60.00%> (-0.01%)	⬇️
linux-stable-cpu	85.43% <60.00%> (-0.02%)	⬇️
linux-stable-gpu	86.15% <60.00%> (-0.04%)	⬇️
linux_examples-gpu	43.12% <60.00%> (+0.02%)	⬆️
macos-cpu	85.24% <60.00%> (-0.02%)	⬇️
olddeps-gpu	76.00% <60.00%> (-0.01%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
torchrl/trainers/helpers/losses.py	42.42% <60.00%> (+2.59%)	⬆️
torchrl/envs/vec_env.py	68.56% <0.00%> (-0.51%)	⬇️

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

[vmoens]

LGTM thanks