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)

ml/run_eval.py

@@ -20,9 +20,9 @@ def main():
     parser.add_argument("--model", type=str, required=True, help="Path to the trained model file (.zip)")
     parser.add_argument("--episodes", type=int, default=3, help="Number of evaluation episodes to run.")
     parser.add_argument("--gui", action="store_true", help="Show the PyBullet GUI during evaluation")
-    parser.add_argument("--num-robots", type=int, default=1, help="Number of robots in the evaluation environment")
     parser.add_argument("--robot-spacing", type=float, default=0.5, help="Spacing between robots in meters")
     parser.add_argument("--start-pose", type=str, choices=["init_deg", "init90_deg"], default="init_deg", help="Initial robot pose at reset")
+    parser.add_argument("--random-command", action="store_true", help="Randomize command samples during evaluation")
     parser.add_argument("--save-metrics", type=str, default=None, help="Optional path to save JSON metrics report")
     args = parser.parse_args()
 
@@ -30,9 +30,9 @@ def main():
         model_path=args.model,
         episodes=args.episodes,
         use_gui=args.gui,
-        num_robots=args.num_robots,
         robot_spacing=args.robot_spacing,
         start_pose=args.start_pose,
+        random_command=args.random_command,
         save_json=args.save_metrics,
     )