- refactored learning function

- remove state_last, use state instead
- added episode history

human_player.py

@@ -42,7 +42,7 @@ class HumanPlayer(APlayer):
 		state_next = self.to_state(state.copy(), move)
 		return state_next, has_moved
 
-	def reward(self, value):
+	def end_game(self, value):
 		if value > 0:
 			print(f"{self.name}, Du hast gewonnen, super!")
 		else:
@@ -57,4 +57,4 @@ if __name__ == '__main__':
 		if not has_moved:
 			break
 
-	p.reward(1.0)
+	p.end_game(1.0)