Re:AlphaStar: Mastering the Real-Time Strategy Game StarCraf...
by CydeWeys on Friday January 25, 2019 @04:03PM
(#19002466)
What they're improving at right now isn't any specific AI model, it's how to train the AI models. It's meta-machine learning. I don't doubt that they can quickly train up a new model under different constraints now that they know how best to train up said models. It's not like they throw away all progress once they change some constraints; far from it.
And then when you drop the APM limit, suddenly all the learned optimal ai strategies start falling apart, and the whole thing has to be relearned.
More annoyingly, there’s not much for human players to learn from innovative ai strategies that are based on inhuman accuracy of play (because we couldn’t possibly execute it).