[X] Integrate existing rendering as Env Wrapper (basicEnv & DilatorEnv) [X] Create The following Schedulers: [X] First come, First Served [X] Shortest Job First [X] Round Robin
[ ] Update project to be regular GymPackage
[X] Implement gym project layout
[X] Test The new layout with
[X] Fix error of s non-deterministic as the observations are not equivalent.
[ ] upload as python package to pip
[ ] Try to use this as gym env with some actions
[ ] Implement different reward functions ???
[ ] Create simple pipeline including tianshou & wandb [ ] Train Simple model on Classic Env [ ] Compare The result to regular scheduler [ ] Take the existing model and run in on large env using Dilation and compare the results [ ] If the results are bad need to add more features (reduce functions) accept max and min