News for hackers. Stuff that matters.
Re:StarCoder and StarCoderBase: 15.5B parameter models with ... by reaperman on Tuesday May 16, 2023 @11:06AM (#35962867)
Not all of them. AlphaStar for StarCraft was largely supervised learning, to mimic top human players. Once it was sufficiently mimicking existing replays, then it switched to Reinforcement Learning.

That's why you see it do "nonsensical" things like destroying the "unbuildable plates" at the bottom of its natural ramp. This 100% wouldn't happen if it had only learned through self-play.

There are no comments on this comment yet.