Changed state output by environments from float to boolean array

kenjyoung · Feb 14, 2020 · ef52ed0 · ef52ed0
1 parent cd40bb5
commit ef52ed0
Show file tree

Hide file tree

Showing 5 changed files with 5 additions and 5 deletions.
diff --git a/minatar/environments/asterix.py b/minatar/environments/asterix.py
@@ -121,7 +121,7 @@ def difficulty_ramp(self):
 
     # Process the game-state into the 10x10xn state provided to the agent and return
     def state(self):
-        state = np.zeros((10,10,len(self.channels)))
+        state = np.zeros((10,10,len(self.channels)),dtype=bool)
         state[self.player_y,self.player_x,self.channels['player']] = 1
         for x in self.entities:
             if(x is not None):

diff --git a/minatar/environments/breakout.py b/minatar/environments/breakout.py
@@ -101,7 +101,7 @@ def difficulty_ramp(self):
 
     # Process the game-state into the 10x10xn state provided to the agent and return
     def state(self):
-        state = np.zeros((10,10,len(self.channels)))
+        state = np.zeros((10,10,len(self.channels)),dtype=bool)
         state[self.ball_y,self.ball_x,self.channels['ball']] = 1
         state[9,self.pos, self.channels['paddle']] = 1
         state[self.last_y,self.last_x,self.channels['trail']] = 1

diff --git a/minatar/environments/freeway.py b/minatar/environments/freeway.py
@@ -92,7 +92,7 @@ def difficulty_ramp(self):
 
     # Process the game-state into the 10x10xn state provided to the agent and return
     def state(self):
-        state = np.zeros((10,10,len(self.channels)))
+        state = np.zeros((10,10,len(self.channels)),dtype=bool)
         state[self.pos,4,self.channels['chicken']] = 1
         for car in self.cars:
             state[car[1],car[0], self.channels['car']] = 1

diff --git a/minatar/environments/seaquest.py b/minatar/environments/seaquest.py
@@ -252,7 +252,7 @@ def difficulty_ramp(self):
 
     # Process the game-state into the 10x10xn state provided to the agent and return
     def state(self):
-        state = np.zeros((10,10,len(self.channels)))
+        state = np.zeros((10,10,len(self.channels)),dtype=bool)
         state[self.sub_y,self.sub_x,self.channels['sub_front']] = 1
         back_x = self.sub_x-1 if self.sub_or else self.sub_x+1
         state[self.sub_y,back_x,self.channels['sub_back']] = 1

diff --git a/minatar/environments/space_invaders.py b/minatar/environments/space_invaders.py
@@ -121,7 +121,7 @@ def difficulty_ramp(self):
 
     # Process the game-state into the 10x10xn state provided to the agent and return
     def state(self):
-        state = np.zeros((10,10,len(self.channels)))
+        state = np.zeros((10,10,len(self.channels)),dtype=bool)
         state[9,self.pos,self.channels['cannon']] = 1
         state[:,:, self.channels['alien']] = self.alien_map
         if(self.alien_dir<0):