Make --num control the number of play games, not just training

--num was declared as "Number of games to play" but the play() call
used a hardcoded 10. Also give --num an int type so it works when
passed on the CLI (range() would otherwise crash on the raw string),
and make --verbose a store_true flag.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PQS7ZHqxQfy5DhKcz2gHau

tic_tac_toe.py

@@ -59,9 +59,9 @@ def play(player_provider: PlayerProvider, k_max=10000, with_debug=False):
 
 if __name__ == '__main__':
 	parser = argparse.ArgumentParser()
-	parser.add_argument("--verbose", default=False, help="Be verbose")
+	parser.add_argument("--verbose", default=False, action='store_true', help="Be verbose")
 	parser.add_argument("--train", default=False, help="Train before play")
-	parser.add_argument("--num", default=5, help="Number of games to play")
+	parser.add_argument("--num", default=5, type=int, help="Number of games to play")
 	parser.add_argument("--human", default=False, help="X-player is human")
 	parser.add_argument("--load", default=True, help="Load experience from previous trainings")
 	args = parser.parse_args()
@@ -104,5 +104,5 @@ if __name__ == '__main__':
 	else:
 		pp = PlayerProvider(p_mx, p_mo)
 
-	play(pp, 10, args.verbose)
+	play(pp, N, args.verbose)