Hacker News Reader

Comment by asar | Hacker News Reader

The live exhibition match definitely made Alphastar look like a machine making the decisions, not a super smart being. The micro was obviously impressive but that should also be the easiest part to master. I share the sentiment that DeepMind is hosting big events to paint a very one-sided picture of man vs machine, so this last win of mana feels oddly satisfying.

View on HN

It is a little disappointing that Mana's win was achieved in part by simply exploiting Alphastar's poor response to the immortal drops by doing it over and over again. In contrast, Lee Sedol's win versus AlphaGo involved profound strategy and a particularly inspired "divine move" that humans get to brag about.

On the one hand, it feels a bit cheap. On the other, getting ahead due to micro but losing due to lack of pattern recognition and problem solving seems like a rather complete demonstration of both the strengths and weaknesses of current AI.

I agree that this makes Lee Sedol's one win against AlphaGo even more impressive. But deepmind also felt ready to host this event and it chose European pros to compete with not Asian pros, who arguably have better micro and innovate a lot of the new meta.

TLO is to Starcraft* as Fan Hui is to Go. They are strong players but not the best. I am guessing that Deepmind knows that the strength of their bot isn't ready to take on the very top players, and wanted to show off against a well-known personality in the Starcraft II scene.

Incidentally, though, the strongest Starcraft II player currently is arguably Serral [1], who is Finnish. He beat the strongest Korean players to win the WCS World Championship last year.

[1] https://liquipedia.net/starcraft2/Serral

* at least TLO's skill level when offracing as Protoss. His main race, Zerg, is very strong, ranked around 70-80th in the world.

Lee Sedol "divine move" actually doesn't work, even human top players would have punished it.

It actually was just a really weird mistake in AlphaGo

Thanks for clarifying that, never really got that that deep into Go.

As they say... there are no good moves in Go/chess/zero-sum games etc. There are only bad moves.

That doesn't prevent professional players such as Gu Li 9p from describing it as a divine move though. And it does feel good for Team Humanity.

They limited the APM to 180 for AlphaStar's input I think. An average professional player consistently plays at 200-300 APM with peak levels generally going to 350-400 APM during engagements.

To me, it seems like AlphaStar is actually at a disadvantage in its ability to micro, and has to make up for this in its macro level strategy.

Most human APM is wasted on "spam clicks". The effective APM, or EPM, is probably quite a bit higher for AlphaStar than for human pros.

TLO and MaNa are in the top 0.01%. They are the best of the best, and then more. The numbers I stated was for the average professional.

When you have geniuses like TLO and MaNa, average APM is more on the level of 300-400 consistent and 500+ in engagements. You're definitely correct that APM is not 100% effectively utilized. I would say maybe around ~40% of actions could generally be considered spam clicks. That still puts AlphaStar at a definite disadvantage in its ability to enact micro level strategy.

Two additional points, aside from APM effectiveness:

- The APM constraint by AlphaStar seems to be average APM (or some variation thereof), while it reached 900+ APM in battles -- again with 100% effectiveness. That's insane and definitely beyond human capacity.

- It didn't waste APM in the early game (when humans are warming up and spamming APM), further leaving slack for when engagements came.

I mean, when gauging practical applications, we shouldn't be too concerned about good reflexes and superhuman effectiveness; however, part of the point here was to gauge other aspects of cognition more related to strategy, large decision spaces, etc; and in this setting it makes sense to constrain those non-strategic (more mechanical/tactical aspects). I'm sure e.g. constraining humans to <300 APM for example would change player style/effectiveness that much, while e.g. the blink stalker micro displayed in Game 4 vs Mana was really reliant on massive parallel single unit/group control (blinking every single low health stalker individually, engaging from multiple sides simultaneously, etc).

Reply on news.ycombinator.com