Refactored

machine_player.py

@@ -2,7 +2,7 @@ import numpy as np
 from a_player import APlayer
 from helper import sample
 from numpy.random import uniform
-
+from state import get_potential_moves
 
 class MachinePlayer(APlayer):
 	class Params:
@@ -56,7 +56,7 @@ class MachinePlayer(APlayer):
 		do_sample = False
 		values = np.array([])
 		# get possible move
-		moves = self.get_potential_moves(state)
+		moves = get_potential_moves(state)
 		if moves.size == 0:
 			return state, False
 
@@ -64,7 +64,7 @@ class MachinePlayer(APlayer):
 		best_value = -1
 		for move in moves:
 			# create hypothetical next state
-			state_next = self.state_from_move(state.copy(), move)
+			state_next = self.to_state(state.copy(), move)
 			# evaluate value
 			value = self.get_value(state_next)
 			if best_value < value:
@@ -91,7 +91,7 @@ class MachinePlayer(APlayer):
 		if self.state is not None:
 			self.state_last = self.state.copy()
 
-		self.state = self.state_from_move(state.copy(), next_move)
+		self.state = self.to_state(state.copy(), next_move)
 
 		# Learn
 		if not is_exp and self.state_last is not None: