Reworked training

new reward/penalty system
learning phases with curriculum learning
new training parameters
cleanup of old code
better logging while training
multiple environments instead of robots (they could bumb into each other)

Robot.py

@@ -84,6 +84,7 @@ class Robot:
         urdf_path: str = cfg.urdf_path
     ):
         self.urdf_path = urdf_path
+        self.start_pose = start_pose
 
         # --- BACKEND FACTORY CREATION ---
         if isinstance(backend_type, BackendType):
@@ -142,7 +143,8 @@ class Robot:
             self.backend.step_simulation()
 
     def reset_to_init(self) -> None:
-        self.current_rad = ri.init_deg.to_rad()
+        pose_deg = ri.init_deg if self.start_pose == "init_deg" else ri.init90_deg
+        self.current_rad = pose_deg.to_rad()
         self.current_pos = kin.ikpyForward(self.current_rad)
         self.set_joint_angles(self.current_rad)
         self.step_sim()