Update app.py

app.py

@@ -84,20 +84,19 @@ class PricingEnv(gym.Env):
         self.data = data
         self.current_step = 0
         self.max_steps = len(data) - 1
-        self.action_space = spaces.Box(low=0, high=100, shape=(1,), dtype=np.float32)
-        self.observation_space = spaces.Box(low=0, high=np.inf, shape=(6,), dtype=np.float32)
+        self.action_space = gym.spaces.Box(low=0, high=100, shape=(1,), dtype=np.float32)
+        self.observation_space = gym.spaces.Box(low=0, high=np.inf, shape=(6,), dtype=np.float32)
 
     def step(self, action):
         reward = self._get_reward(action)
         self.current_step += 1
         done = self.current_step >= self.max_steps
         obs = self._get_observation()
-        return obs, reward, done, False, {}  # Added False for truncated flag
+        return obs, reward, done, {}  # Removed the 'truncated' flag for compatibility
 
-    def reset(self, seed=None, options=None):
-        super().reset(seed=seed)
+    def reset(self):
         self.current_step = 0
-        return self._get_observation(), {}  # Return observation and info dict
+        return self._get_observation()
 
     def _get_observation(self):
         if self.current_step > self.max_steps: