- fixed human player

human_player.py

@@ -42,7 +42,7 @@ class HumanPlayer(APlayer):
 		state_next = self.to_state(state.copy(), move)
 		return state_next, has_moved
 
-	def end_game(self, value):
+	def end_game(self, value, state: np.array):
 		if value > 0:
 			print(f"{self.name}, Du hast gewonnen, super!")
 		else:

tic_tac_toe.py

@@ -79,11 +79,11 @@ else:
 	o_values = {}
 
 p_hx = HumanPlayer(mark='X', name="Jens")
-p_mx = MachinePlayer(mark='X', params=MachinePlayer.Params(p_explore=0.2, alpha=0.1), values=x_values)
-p_mo = MachinePlayer(mark='O', params=MachinePlayer.Params(p_explore=0.2, alpha=0.1), values=o_values)
+p_mx = MachinePlayer(mark='X', params=MachinePlayer.Params(p_explore=0.1, alpha=0.1), values=x_values)
+p_mo = MachinePlayer(mark='O', params=MachinePlayer.Params(p_explore=0.1, alpha=0.1), values=o_values)
 
 if do_training:
-	play(PlayerProvider(p_mx, p_mo), 5000, True)
+	play(PlayerProvider(p_mx, p_mo), 50000, False)
 
 	# Values after training
 	# Convert and write JSON object to file