Update app.py

app.py

@@ -146,25 +146,40 @@ def optimize_signal_rl(congestion_level):
         model.learn(total_timesteps=1000)
 
         # Reset the environment and get the initial observation
-        obs = env.reset()  # No need to unpack anything; this gives the observation array
-        logging.debug(f"Reset observation: {obs}, type: {type(obs)}, shape: {np.shape(obs)}")
+        obs = env.reset()  # `obs` should be a 2D array (vectorized environment)
+        if not isinstance(obs, np.ndarray) or obs.ndim != 2:  # Validate obs shape
+            raise ValueError(f"Unexpected observation shape: {obs}, type: {type(obs)}")
+
+        logging.info(f"Initial observation: {obs}")
 
         # RL Optimization loop
         for _ in range(10):
-            action, _ = model.predict(obs, deterministic=True)  # Predict action
-            obs, rewards, dones, infos = env.step(action)  # Step environment
+            # Predict action and perform step
+            action, _ = model.predict(obs, deterministic=True)
+            obs, rewards, dones, infos = env.step(action)
+            
+            if not isinstance(obs, np.ndarray) or obs.ndim != 2:  # Validate obs shape again
+                raise ValueError(f"Unexpected observation after step: {obs}, type: {type(obs)}")
             
-            # Flatten the observation for the next step
+            # Flatten the observation for easier handling
             obs = obs.flatten()
 
-            # If any environment is done, stop
-            if dones[0]:
+            logging.debug(f"Step results - Obs: {obs}, Reward: {rewards}, Done: {dones}, Info: {infos}")
+
+            if dones[0]:  # Stop if the environment signals it's done
                 break
 
-        # Get the optimal duration
-        optimal_duration = int(obs[1]) if len(obs) > 1 else 30  # Use default if obs is incorrect
+        # Get optimal signal duration
+        if len(obs) > 1:  # Ensure the array has enough elements
+            optimal_duration = int(obs[1])
+        else:
+            raise ValueError(f"Observation array too short: {obs}")
+
         return f"Green for {optimal_duration}s, Red for {60 - optimal_duration}s"
 
+    except ValueError as ve:
+        logging.error(f"Value error: {ve}")
+        return "Error: Unexpected values encountered during optimization."
     except Exception as e:
         logging.error(f"Error optimizing signal with RL: {e}")
         return "Error in RL Optimization"