Re:AlphaStar: Mastering the Real-Time Strategy Game StarCraf...
by georgeek on Friday January 25, 2019 @07:52AM
(#18997481)
TLO is a Zerg player, so he probably does a lot more errors when playing Protoss. Also, every top player estimates when to do a sequence of actions and spams it a few times to maximize the chance of execution. Meanwhile Alphastar only has to do that once.
Re:AlphaStar: Mastering the Real-Time Strategy Game StarCraf...
by integricho on Friday January 25, 2019 @02:04AM
(#18996115)
Yes,could that bug be the reason for the AI getting to 1000APM?
Fair point about humans needing minor adjustments though. Another comment also mentioned a bug in the APM measurement: https://news.ycombinator.com/item?id=18994350