Update app.py

app.py

@@ -38,7 +38,7 @@ class Ant:
         self.path_home = []
         self.role = "explorer"
         self.communication_range = 10
-        self.q_table = np.zeros((GRID_SIZE, GRID_SIZE, 4))
+        self.q_table = {}  # Changed to dictionary for flexible indexing
 
     def perceive_environment(self, pheromone_grid, ants):
         self.food_pheromone = pheromone_grid[self.position[0], self.position[1], 0]
@@ -48,13 +48,13 @@ class Ant:
         # Perceive nearby ants
         self.nearby_ants = [ant for ant in ants if distance.euclidean(self.position, ant.position) <= self.communication_range]
 
-    def act(self, pheromone_grid):
+     def act(self, pheromone_grid):
         possible_actions = self.get_possible_actions()
         
         if random.random() < self.genome['exploration_rate']:  
             action = random.choice(possible_actions)
         else:
-            q_values = [self.q_table[self.position[0], self.position[1], action] for action in possible_actions]
+            q_values = [self.get_q_value(action) for action in possible_actions]
             action = possible_actions[np.argmax(q_values)]
 
         reward = self.calculate_reward()
@@ -62,24 +62,26 @@ class Ant:
 
         return action
 
-    def calculate_reward(self):
-        if self.carrying_food:
-            return 10
-        elif self.position in FOOD_SOURCES:
-            return 20
-        elif self.position in OBSTACLES:
-            return -10
-        else:
-            return -1 + self.food_pheromone - self.danger_pheromone + 0.5 * self.exploration_pheromone
+    def get_q_value(self, action):
+        return self.q_table.get((self.position, action), 0)
 
     def update_q_table(self, action, reward):
-        self.q_table[self.position[0], self.position[1], action] = (
-            (1 - self.genome['learning_rate']) * self.q_table[self.position[0], self.position[1], action] +
-            self.genome['learning_rate'] * (reward + self.genome['discount_factor'] * np.max(self.q_table[self.position[0], self.position[1]]))
-        )
+        current_q = self.get_q_value(action)
+        max_future_q = max([self.get_q_value(future_action) for future_action in self.get_possible_actions()])
+        
+        new_q = (1 - self.genome['learning_rate']) * current_q + \
+                self.genome['learning_rate'] * (reward + self.genome['discount_factor'] * max_future_q)
+        
+        self.q_table[(self.position, action)] = new_q
 
     def get_possible_actions(self):
-        return list(env_graph.neighbors(self.position))
+        x, y = self.position
+        possible_actions = []
+        for dx, dy in [(0, 1), (1, 0), (0, -1), (-1, 0)]:  # right, down, left, up
+            new_x, new_y = x + dx, y + dy
+            if 0 <= new_x < GRID_SIZE and 0 <= new_y < GRID_SIZE and (new_x, new_y) not in OBSTACLES:
+                possible_actions.append((new_x, new_y))
+        return possible_actions
 
     def update(self, pheromone_grid, ants):
         self.perceive_environment(pheromone_grid, ants)