- refactored learning function

- remove state_last, use state instead - added episode history
2024-06-11 09:00:41 +02:00
parent 73f59f25fc
commit 53e4d91ff8
4 changed files with 47 additions and 28 deletions
@@ -43,14 +43,14 @@ def play(player_provider: PlayerProvider, k_max=10000, with_debug=False):
 				if not has_moved:
 					if with_debug:
 						print(f"{player.mark}: No more moves")
-						player.reward(0.0)
-						other_player.reward(0.0)
+						player.end_game(0.0)
+						other_player.end_game(0.0)
 					run = False
 				if player.has_won(state):
 					if with_debug:
 						print(f"{player.mark}: Has won the game")
-						player.reward(1.0)
-						other_player.reward(0.0)
+						player.end_game(1.0)
+						other_player.end_game(0.0)
 					run = False

 				other_player = player