changed learning to array data only (not visual), changed some collisions

train_bot.py

@@ -4,18 +4,25 @@ from stable_baselines3 import PPO
 from stable_baselines3.common.callbacks import BaseCallback
 from flower_game_env import FlowerGameEnv
 
-
-# ---- Dein Spielbereich (anpassen!) ----
+# ---- Spielbereich ----
 monitor_area = {"top": 120, "left": 330, "width": 1900, "height": 1263}
-env = FlowerGameEnv(monitor_area)
+ui_exclude_rects = []  # optional: Pixel oder [0..1]-normiert
+
+time.sleep(3)
+
+# Env mit fester Referenzgröße (Baseline)
+env = FlowerGameEnv(
+    monitor_area,
+    ui_exclude_rects=ui_exclude_rects,
+    ref_size=(1900, 1263),
+)
+
 saved_model_name = "flower_bot"
-zip_file = saved_model_name + ".zip"
+zip_file = f"{saved_model_name}.zip"
 
 
 class TimeBasedCheckpoint(BaseCallback):
-    """
-    Speichert das Modell alle 'save_every_secs' Sekunden in 'save_prefix' + Timestamp.
-    """
+    """Speichert das Modell alle 'save_every_secs' Sekunden nach save_prefix.zip"""
     def __init__(self, save_every_secs=60, save_prefix=saved_model_name, verbose=1):
         super().__init__(verbose)
         self.save_every_secs = save_every_secs
@@ -25,7 +32,7 @@ class TimeBasedCheckpoint(BaseCallback):
     def _on_step(self) -> bool:
         now = time.time()
         if now - self._last_save >= self.save_every_secs:
-            fname = f"{self.save_prefix}"
+            fname = self.save_prefix
             if self.verbose:
                 print(f"[Autosave] Saving model to {fname}.zip")
             self.model.save(fname)
@@ -33,17 +40,16 @@ class TimeBasedCheckpoint(BaseCallback):
         return True
 
 
-# --- Laden, falls Datei vorhanden ---
+# --- Laden/Starten ---
 if os.path.exists(zip_file):
     print(f"Lade existierendes Modell aus {zip_file}")
-    model = PPO.load(zip_file, env=env)  # Weitertrainieren mit neuem Env
+    model = PPO.load(zip_file, env=env)  # weitertrainieren
 else:
     print("Starte neues Modell")
-    # CNN + Dict-Observation → Verwende 'MultiInputPolicy'
     model = PPO("MultiInputPolicy", env, verbose=2)
 
-# Trainieren mit Autosave (jede Minute)
-model.learn(total_timesteps=500_000, callback=TimeBasedCheckpoint(100, "flower_bot"))
+# Trainieren mit Autosave
+model.learn(total_timesteps=500_000, callback=TimeBasedCheckpoint(100, saved_model_name))
 
 # Abschluss-Speicherstand
 model.save("flower_bot_final")