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/evaluate.py

@@ -13,10 +13,9 @@ def evaluate(
     model_path: str,
     episodes: int = 5,
     use_gui: bool = True,
-    num_robots: int = 16,  # Default to 16 to match your trained (352,) observation space
     robot_spacing: float = 0.5,
     start_pose: str = "init_deg",
-    random_command: bool = True,
+    random_command: bool = False,
     save_json: Optional[str] = None,
 ) -> Dict[str, Any]:
     try:
@@ -36,7 +35,6 @@ def evaluate(
     env = JackBotEnv(
         use_gui=use_gui,
         random_command=random_command,
-        num_robots=num_robots,
         robot_spacing=robot_spacing,
         start_pose=start_pose,
     )
@@ -72,7 +70,6 @@ def evaluate(
     metrics = {
         "model_path": str(model_path),
         "episodes_evaluated": episodes,
-        "num_robots": num_robots,
         "mean_reward": float(np.mean(episode_rewards)),
         "std_reward": float(np.std(episode_rewards)),
         "mean_episode_length": float(np.mean(episode_lengths)),