[WIP] ReinforcementLearning.jl integration

[rejuvyesh]

I realized that CommonRLInterface.jl never settled on what to do with continuous action spaces, so directly integrating with RLBase from ReinforcementLearning.jl.

Will add tests and examples with PPO and DDPG.

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.31%. Comparing base (5563639) to head (eb379f6).
Report is 411 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main       #9      +/-   ##
==========================================
- Coverage   92.48%   92.31%   -0.17%     
==========================================
  Files          81       81              
  Lines        4005     3761     -244     
==========================================
- Hits         3704     3472     -232     
+ Misses        301      289      -12     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[findmyway]

Note that you are using the discrete version of PPO here. But the cart pole env here seems to be a continuous version. (The actions space is [-1.0, 1.0]). So you may take reference from https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/935f68b6cb378f9929a8d9914eb388e86213c86d/src/ReinforcementLearningExperiments/deps/experiments/experiments/Policy%20Gradient/JuliaRL_PPO_Pendulum.jl#L43-L50

[rejuvyesh]

Good point! Thanks for checking in. Although currently I also need to define the reward/cost function for cartpole on Dojo side.

[janbruedigam]

We should probably rethink the interface to ReinforcementLearning.jl once their updates are done (JuliaReinforcementLearning/ReinforcementLearning.jl#614)