fix custom gamma in rl

[BartekRoszak]

What does this PR do?

I didn't make an issue as the bug seems to be obvious.
So far in a few rl models, custom gamma could be set in init but then was not passed to loss computation function.
This PR fixes it.

Fixes # (issue)

Before submitting

• Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests? [not needed for typos/docs]
• Did you verify new and existing tests pass locally with your changes?
• If you made a notable change (that affects users), did you update the CHANGELOG?

PR review

• Is this pull request ready for review? (if not, please submit in draft mode)

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

Did you have fun?

Make sure you had fun coding 🙃

[codecov]

Codecov Report

Merging #550 (cb1aa65) into master (b9d5f5e) will decrease coverage by 0.07%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #550      +/-   ##
==========================================
- Coverage   77.60%   77.53%   -0.08%     
==========================================
  Files         115      115              
  Lines        6707     6707              
==========================================
- Hits         5205     5200       -5     
- Misses       1502     1507       +5     

Flag	Coverage Δ
cpu	?
pytest	?
unittests	77.53% <100.00%> (+0.44%)	⬆️

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

Impacted Files	Coverage Δ
pl_bolts/models/rl/double_dqn_model.py	95.65% <100.00%> (ø)
pl_bolts/models/rl/dqn_model.py	78.48% <100.00%> (ø)
pl_bolts/models/rl/per_dqn_model.py	86.66% <100.00%> (ø)
pl_bolts/utils/warnings.py	38.46% <0.00%> (-61.54%)	⬇️
...s/models/detection/components/_supported_models.py	71.42% <0.00%> (-28.58%)	⬇️
pl_bolts/datasets/mnist_dataset.py	36.36% <0.00%> (-9.10%)	⬇️
pl_bolts/models/detection/faster_rcnn/backbones.py	84.61% <0.00%> (-7.70%)	⬇️
pl_bolts/transforms/dataset_normalizations.py	80.00% <0.00%> (-5.00%)	⬇️
pl_bolts/callbacks/vision/image_generation.py	87.87% <0.00%> (-3.04%)	⬇️
..._bolts/models/self_supervised/simclr/transforms.py	75.71% <0.00%> (-2.86%)	⬇️
... and 16 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update b9d5f5e...c8000de. Read the comment docs.

[akihironitta]

@BartekRoszak LGTM. Thank you for your contribution!

[akihironitta]

@Borda Could I have your review here?