Lowered number of actions

games/racecar.py

@@ -19,10 +19,7 @@ class MuZeroConfig:
 
         ### Game
         self.observation_shape = (3, 96, 96)  # Dimensions of the game observation, must be 3D (channel, height, width). For a 1D array, please reshape it to (1, 1, length of array)
-        # Actions discretised in steps of 0.25:
-        # 9 for steering; [-1.0, -0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0]
-        # 5 for gas, 5 for brakes; [0.0, 0.25, 0.5, 0.75, 1.0]
-        self.action_space = list(range(9 + 5 + 5))  # Fixed list of all possible actions. You should only edit the length
+        self.action_space = list(range(5))  # Fixed list of all possible actions. You should only edit the length
         self.players = list(range(1))  # List of players. You should only edit the length
         self.stacked_observations = 5  # Number of previous observations and previous actions to add to the current observation
 
@@ -168,7 +165,7 @@ class Game(AbstractGame):
         Returns:
             An array of integers, subset of the action space.
         """
-        return list(range(9 + 5 + 5))
+        return list(range(5))
 
     def reset(self):
         """
@@ -231,16 +228,13 @@ class Game(AbstractGame):
             Array with three elements: steering in range [-1, 1], gas in range [0, 1], braking in range [0, 1]
         """
 
-        steering = 0
-        gas = 0
-        brakes = 0
+        possibleActions = [
+            [0, 0, 0],
+            [-1, 0, 0],
+            [1, 0, 0],
+            [0, 1, 0],
+            [0, 0, 1],
+        ]
 
-        if (action_number <= 9):
-            steering = -1 + action_number * 0.25
-        elif (action_number <= 14):
-            gas = (action_number - 10) * 0.25
-        else:
-            brakes = (action_number - 15) * 0.25
-
-        actionFormatted = [steering, gas, brakes]
+        actionFormatted = possibleActions[action_number]
         return actionFormatted