add learning after episode

player_provider.py

@@ -1,3 +1,5 @@
+import numpy as np
+
 from a_player import APlayer
 from numpy.random import uniform
 
@@ -10,15 +12,15 @@ class PlayerProvider:
 		for p in self.players:
 			p.set_debug(with_debug)
 
-	def choose(self) -> list[APlayer]:
+	def choose(self, state: np.array) -> list[APlayer]:
 		# Wer fängt an?
 		players = self.players
 		if uniform() < 0.5:
 			players.reverse()
 
 		result = players
-		players[0].new_game()
-		players[1].new_game()
+		players[0].new_game(state)
+		players[1].new_game(state)
 
 		return result