go

agent_afterstate.py

@@ -11,7 +11,7 @@ class Action(IntEnum):
     RIGHT = 4
 
 class afterstateAgent:
-    def __init__(self, mat, TD_lambda = 0.0, alpha = 0.0025, gamma = 0.95, epsilon = 0.01, verbose= True, symmetric=True):
+    def __init__(self, mat, TD_lambda = 0.0, alpha = 0.0025, gamma = 0.95, epsilon = 0.01, verbose= True, symmetric=True, tuple = 2):
         self.state_per_tile = 12
         self.commands = { Action.UP: up, Action.DOWN: down, Action.LEFT: left, Action.RIGHT: right}
         self.alpha = alpha
@@ -21,11 +21,12 @@ class afterstateAgent:
         self.TD_lambda = TD_lambda
         self.forget = self.TD_lambda
         self.symmetric = symmetric
-        if self.symmetric:
-            # self.tuple = self._tuple_advance()
+        if tuple==0:
+             self.tuple = self._tuple() 
+        elif tuple == 1:
             self.tuple = self._tuple_advance()
         else:
-            self.tuple = self._tuple()
+            self.tuple = self._tuple_advance_plus()
         if verbose:
             print(len(self.tuple))
         self.W = self._generate_dict()
@@ -58,7 +59,14 @@ class afterstateAgent:
         print(list)
         return list
 
+    
     def _tuple_advance(self):
+        return [[(0,0),(1,0),(2,0),(3,0)],\
+                    [(0,1),(1,1),(2,1),(3,1)],\
+                    [(0,1),(1,1),(2,1),(0,2),(1,2),(2,2)],\
+                    [(0,2),(1,2),(2,2),(0,3),(1,3),(2,3)]]
+
+    def _tuple_advance_plus(self):
         return [[(0,0),(1,0),(2,0),(3,0),(3,1),(2,1)],\
                     [(0,1),(1,1),(2,1),(3,1),(3,2),(2,2)],\
                     [(0,1),(1,1),(2,1),(0,2),(1,2),(2,2)],\

puzzle.py

@@ -177,6 +177,7 @@ if __name__ == '__main__':
     parser.add_option("-t", "--train", dest="train", help ="training episodes") 
     parser.add_option("-s", "--symmetric", dest="symmetric", help ="symmetric sampling")
     parser.add_option("-e", "--epsilon", dest="epsilon", help ="epsilon the exploration")
+    parser.add_option("-u", "--tuple", dest="tuple", help ="the tuple to use")
     (options,args)= parser.parse_args()
     print(vars(options))
     start_time = time.time()