Refactored

machine_player.py

@@ -6,8 +6,8 @@ from state import get_potential_moves
 
 class MachinePlayer(APlayer):
 	class Params:
-		def __init__(self, p_exp, alpha):
-			self.p_exp = p_exp
+		def __init__(self, p_explore, alpha):
+			self.p_exp = p_explore
 			self.alpha = alpha
 
 	def __init__(self, mark, params: Params, values):
@@ -53,7 +53,6 @@ class MachinePlayer(APlayer):
 		self.state_last = None
 
 	def move(self, state: np.array):
-		do_sample = False
 		values = np.array([])
 		# get possible move
 		moves = get_potential_moves(state)
@@ -74,13 +73,11 @@ class MachinePlayer(APlayer):
 
 		next_move = best_move
 		is_exp = False
+		# Randomly perform exploratory move
 		if uniform() < self.params.p_exp:
 			index = np.random.randint(len(moves))
 			next_move = moves[index]
 			is_exp = best_move != next_move
-		elif do_sample:
-			index = sample(values)
-			next_move = moves[index]
 
 		if self.with_debug:
 			print(f"{self.mark}: Values    = {values}")