RL models clean up

[djbyrne]

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 to update the docs?
• Did you write any new necessary tests?

What does this PR do?

Refactors RL models to use train_batch structure as seen in #107

general clean up of docstrings and methods

PR review

Did you have fun?

👍

[pep8speaks]

Hello @djbyrne! Thanks for updating this PR.

There are currently no PEP 8 issues detected in this Pull Request. Cheers! 🍻

Comment last updated at 2020-07-14 15:48:24 UTC

[codecov]

Codecov Report

Merging #112 into master will increase coverage by 0.00%.
The diff coverage is 86.48%.

@@           Coverage Diff           @@
##           master     #112   +/-   ##
=======================================
  Coverage   91.91%   91.92%           
=======================================
  Files          77       78    +1     
  Lines        3944     4010   +66     
=======================================
+ Hits         3625     3686   +61     
- Misses        319      324    +5     

Flag	Coverage Δ
#unittests	91.92% <86.48%> (+<0.01%)	⬆️

Impacted Files	Coverage Δ
pl_bolts/models/rl/double_dqn_model.py	94.44% <ø> (+20.25%)	⬆️
pl_bolts/models/rl/n_step_dqn_model.py	100.00% <ø> (ø)
pl_bolts/models/rl/noisy_dqn_model.py	95.83% <ø> (+18.05%)	⬆️
pl_bolts/models/rl/per_dqn_model.py	57.14% <9.09%> (-23.81%)	⬇️
pl_bolts/models/rl/dqn_model.py	82.88% <75.00%> (+0.35%)	⬆️
pl_bolts/datamodules/experience_source.py	97.72% <97.72%> (ø)
pl_bolts/datamodules/__init__.py	100.00% <100.00%> (ø)
pl_bolts/models/rl/common/experience.py	97.08% <100.00%> (+0.14%)	⬆️
pl_bolts/models/rl/reinforce_model.py	97.43% <100.00%> (+0.02%)	⬆️
...l_bolts/models/rl/vanilla_policy_gradient_model.py	96.55% <100.00%> (-1.16%)	⬇️
... and 11 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 024b574...79e7e5c. Read the comment docs.

[Borda]

shall this be rater at the beginning rather than the end?

[djbyrne]

Im not sure I understand

[Borda]

that you reset the episode_steps and the other when it is done... so shall it be more logical to reset it before you start rather?

[djbyrne]

Ah I see. The done is a local variable that is retrieved after taking a step on line 72, so the done check must come after that, so I think it makes more sense to do it at the end

[mergify]

This pull request is now in conflict... :(