Hacker News new | ask | show | jobs
by ipsum2 2197 days ago
Alpha Go Zero*, which was trained from scratch, without human games.

I've also heard rumors that AlphaStar (https://deepmind.com/blog/article/alphastar-mastering-real-t...) was essentially put on hold because it was too expensive to improve/train. The bot wasn't able to beat StarCraft champions and _only_ got to a grandmaster level.
5 comments
Symmetry 2197 days ago
Alpha Go Zero used a combination of deep learning within a classical AI Monte Carlo simulation framework. Without a similarly effective framework its not surprising that Alpha Star wasn't able to achieve similar success. I've watched a lot of Alpha Star replays and the lapses in forethought glare through pretty regularly, though other aspects of its judgement (not just reflexes!) seem frankly super human.
link
embrassingstuff 2196 days ago
Why was MCTS (or some search variant) not used in alphastar ?

(Sure, u need to somehow roll forward and rollback the StarCraft world, but for Atari using MCTS was shown to be an order of magnitude more efficient )

I have also seen comments that the search width is too large, or maybe academic purity consideration?

link
__s 2197 days ago
https://www.youtube.com/watch?v=nbiVbd_CEIA

At the last Blizzcon they had it around. The setup wasn't ideal, so Serral (won world finals in 2018, reached semifinals in 2019) wasn't really happy with how he played, but it won

This was also a version where they'd worked on preventing its ability to micro at quadruple digit apm

link
ajnin 2196 days ago
That match was still arguably not fair for the human because of the imperfect input and outputs he had to deal with. In the end I'm not sure it makes sense to put artificial handicaps on the machine to leave the human a chance. It's like a swimming race between a fish and some land animal but the fish is not allowed to use its fins. Sure the other guy has a better chance to win, but, what does that measure really?
link
qayxc 2197 days ago
The main issue is that they need to retrain their bots for each new map, which would mean excessive training every time the map-pool changes (e.g. every 3 months or so IIRC).

I'd even argue that they missed their goal by a long shot if their system isn't able to play arbitrary maps - every human player can do that no problem.

link
bsaul 2197 days ago
Interesting ! i didn't understand why they stopped the alphastar project. They pretended they reached their goal, but clearly haven't.
link
NVHacker 2197 days ago
The goal was never to beat all pros. https://deepmind.com/blog/article/AlphaStar-Grandmaster-leve...
link
sabas123 2197 days ago
on a side note, I'm still disappointed to see that they didn't improve on the EAPM restriction to truly show they can beat humans without machine-y advantages.

Still what they have accomplished is a miracle.

link
phonon 2197 days ago
The version that later went on ladder anonymously used human-like E/APM.

https://storage.googleapis.com/deepmind-media/research/alpha...

link
empath75 2196 days ago
playing at grandmaster level is a pretty astounding achievement.
link