update

markub3327 · Feb 27, 2024 · 698f1b3 · 698f1b3
1 parent 30ac897
commit 698f1b3
Showing 1 changed file with 19 additions and 15 deletions.
diff --git a/flappy_bird_gymnasium/envs/flappy_bird_env.py b/flappy_bird_gymnasium/envs/flappy_bird_env.py
@@ -272,25 +272,29 @@ def step(
             # find ray closest to the obstacle
             min_index = np.argmin(obs)
             min_value = obs[min_index] * LIDAR_MAX_DISTANCE
-            mean_value = np.mean(obs) * LIDAR_MAX_DISTANCE
+            if "pipe_mean_value" in self._statistics:
+                self._statistics["pipe_mean_value"] = self._statistics["pipe_mean_value"] * 0.99 + (np.mean(obs) * LIDAR_MAX_DISTANCE) * (1 - 0.99)
+            else:
+                self._statistics["pipe_mean_value"] = np.mean(obs) * LIDAR_MAX_DISTANCE
 
             # In the gap
             if ((self._player_x + PLAYER_WIDTH) - up_pipe['x']) >= 0 and (self._player_x - up_pipe['x']) <= PIPE_WIDTH:
-                if "pipe_min_value" in self._nearest_stats:
-                    if min_value < self._nearest_stats["pipe_min_value"]:
-                        self._nearest_stats["pipe_min_value"] = min_value
-                        # print(f"NEAREST TO PIPE !!!: obs: [{min_index}, {min_value}, {mean_value}], up_pipe: [{up_pipe['x']}, {up_pipe['y']+PIPE_HEIGHT}], low_pipe: {low_pipe}, player: [{self._player_x}, {self._player_y}]")
+                if "pipe_min_value" in self._statistics:
+                    if min_value < self._statistics["pipe_min_value"]:
+                        self._statistics["pipe_min_value"] = min_value
+                        self._statistics["pipe_min_index"] = min_index
+                        # print(f"NEAREST TO PIPE !!!: obs: [{min_index}, {min_value}, {self._statistics['pipe_mean_value']}], up_pipe: [{up_pipe['x']}, {up_pipe['y']+PIPE_HEIGHT}], low_pipe: {low_pipe}, player: [{self._player_x}, {self._player_y}]")
                 else:
-                    self._nearest_stats["pipe_min_value"] = min_value
+                    self._statistics["pipe_min_value"] = min_value
 
             # Nearest to the ground
             diff = np.abs(self._player_y - self._ground['y'])
-            if "ground_min_value" in self._nearest_stats:
-                if diff < self._nearest_stats["ground_min_value"]:
-                    self._nearest_stats["ground_min_value"] = diff
-                   #  print(f"NEAREST TO GROUND !!!: obs: [{min_index}, {min_value}, {mean_value}], up_pipe: [{up_pipe['x']}, {up_pipe['y']+PIPE_HEIGHT}], low_pipe: {low_pipe}, player: [{self._player_x}, {self._player_y}], Ground: {self._player_y - self._ground['y']}")
+            if "ground_min_value" in self._statistics:
+                if diff < self._statistics["ground_min_value"]:
+                    self._statistics["ground_min_value"] = diff
+                    # print(f"NEAREST TO GROUND !!!: obs: [{min_index}, {min_value}, {self._statistics['pipe_mean_value']}], up_pipe: [{up_pipe['x']}, {up_pipe['y']+PIPE_HEIGHT}], low_pipe: {low_pipe}, player: [{self._player_x}, {self._player_y}], Ground: {diff}")
             else:
-                self._nearest_stats["ground_min_value"] = diff
+                self._statistics["ground_min_value"] = diff
 
 
         # agent touch the top of the screen as punishment
@@ -304,14 +308,14 @@ def step(
             terminal = True
             self._player_vel_y = 0
             if self._debug:
-                if (((self._player_x + PLAYER_WIDTH) - up_pipe['x']) > 0
+                if (((self._player_x + PLAYER_WIDTH) - up_pipe['x']) >= (0 + (PLAYER_WIDTH / 3))
                         and (self._player_x - up_pipe['x']) <= (PIPE_WIDTH - (PLAYER_WIDTH / 3))):
                     print("BETWEEN PIPES")
-                elif ((self._player_x + PLAYER_WIDTH) - up_pipe['x']) <= 0:
+                elif ((self._player_x + PLAYER_WIDTH) - up_pipe['x']) < (0 + (PLAYER_WIDTH / 3)):
                     print("IN FRONT OF")
                 elif (self._player_x - up_pipe['x']) > (PIPE_WIDTH - (PLAYER_WIDTH / 3)):
                     print("BEHIND")
-                print(f"obs: [{min_index}, {min_value}, {mean_value}], Ground: {self._player_y - self._ground['y']}")
+                print(f"obs: [{self._statistics['pipe_min_index']}, {self._statistics['pipe_min_value']}, {self._statistics['pipe_mean_value']}], Ground: {self._statistics['ground_min_value']}")
 
         info = {"score": self._score}
 
@@ -337,7 +341,7 @@ def reset(self, seed=None, options=None):
         self._score = 0
 
         if self._debug:
-            self._nearest_stats = {}
+            self._statistics = {}
 
         # Generate 3 new pipes to add to upper_pipes and lower_pipes lists
         new_pipe1 = self._get_random_pipe()