Plays "normally" (cautiously since the bot is so good) until 7:00 accumulating gold for enough items to more safely eliminate the creeps: https://www.youtube.com/watch?v=R85WVTFPmRE&t=420s
I think these kinds of adversarial examples will be extremely common in production models. People won’t be crafting images that fool the model into thinking you’re a stop sign; they’ll discover that when the human isn’t paying attention, you can run in front of a Tesla with a group of friends and it veers into oncoming traffic. (Terrible made-up example, but I’m pretty sure that it’s a losing game to play “can we think of all possible cases we need to train for ahead of time?”)
You can watch Black beat the bot in a fair game here, though, which I find immensely satisfying: https://youtu.be/qov1NXsTSbs?t=88 IIRC he was one of only like... five? (less?) who managed to win one game.