Update app.py

app.py

@@ -128,7 +128,6 @@ class TrafficSimEnv(gym.Env):
 # Prior to commit had a lot of errors regarding expected output errors
 def optimize_signal_rl(congestion_level):
     try:
-
         # Map congestion levels (string to numeric)
         congestion_map = {
             "Low": 2,
@@ -139,7 +138,6 @@ def optimize_signal_rl(congestion_level):
         if isinstance(congestion_level, str):
             congestion_level = congestion_map.get(congestion_level, 5)  # Default to "Medium" if unrecognized
 
-        
         # Create environment
         env = DummyVecEnv([lambda: TrafficSimEnv(congestion_level)])
 
@@ -150,25 +148,25 @@ def optimize_signal_rl(congestion_level):
         model.learn(total_timesteps=1000)
 
         # Reset the environment
-        obs, info = env.reset()
-        obs = obs[0]  # Extract first observation from batch
+        obs = env.reset()  # Returns a single value (batch of observations)
 
+        # RL Optimization loop
         for _ in range(10):
             action, _ = model.predict(obs, deterministic=True)
-            obs, reward, done, truncated, info = env.step(action)
+            obs, rewards, dones, infos = env.step(action)
 
-            # Unpack single observations (adjust for DummyVecEnv behavior)
+            # Unpack single observation and reward (batch size of 1)
             obs = obs[0]
-            reward = reward[0]
-            done = done[0]
-            truncated = truncated[0]
+            reward = rewards[0]
+            done = dones[0]
 
             # Debugging logs for better tracking
             logging.debug(f"Action: {action}, Observation: {obs}, Reward: {reward}, Done: {done}")
 
-            if done or truncated:
+            if done:
                 break
 
+        # Get optimal duration
         optimal_duration = int(obs[1]) if len(obs) > 1 else 30
         return f"Green for {optimal_duration}s, Red for {60 - optimal_duration}s"