DeepMind StarCraft II Demonstration [video] • Hacker News Board

Re: DeepMind StarCraft II Demonstration [video]

#121

Post by orbifold » Fri, Jan 25, 2019, 7:33 PM UTC

Dylan16807 wrote: post #119

orbifold wrote: post #106

Earlier quoted context omitted.

Those were not one and the same agent. If you look at the figure they released on their website the given agent would probably always have gone for a lot of blink stalkers.

We're talking about the whole package of the AI, what the entire system is capable of, so that technical detail doesn't affect kmnc's point or mine. The biggest effect is that it's harder to change strategy midgame, which is not all that critical.

It makes the trained agent much less like a human, individual agents are not creative, they‘ve just learned to execute a certain build order. It might turn out that this is enough coupled with flawless execution and micro.

Re: DeepMind StarCraft II Demonstration [video]

#122

Post by xster » Fri, Jan 25, 2019, 7:45 PM UTC

kmnc wrote: post #45

Very impressive... but it seems like the AI relies entirely on abusing blink stalkers which with perfect micro is basically impossible to counter. It is no surprise it can crush pros when it has perfect timing and zero mistakes in using these units. I think the coolest thing is how the play of AI mirrors a similar style to how pros have developed (Micro harrasing early, early expansions, a very good understanding of…

Ya, that one game was a bit... 'fresh'. But saying that it relies 'entirely' on abusing blink stalkers isn't quite right.

It did it in 1 game of the 5 they were showing.

Re: DeepMind StarCraft II Demonstration [video]

#123

Post by Dylan16807 » Fri, Jan 25, 2019, 10:23 PM UTC

orbifold wrote: post #121

Dylan16807 wrote: post #119

Earlier quoted context omitted.

We're talking about the whole package of the AI, what the entire system is capable of, so that technical detail doesn't affect kmnc's point or mine. The biggest effect is that it's harder to change strategy midgame, which is not all that critical.

It makes the trained agent much less like a human, individual agents are not creative, they‘ve just learned to execute a certain build order. It might turn out that this is enough coupled with flawless execution and micro.

"A human agent isn't creative, it just has a set of initial build orders it developed and picks one before the game starts, and after that it adapts to the situation weighted by the units it prefers."

Also the execution of the build order is nowhere near flawless.

Re: DeepMind StarCraft II Demonstration [video]

#124

Post by gambler » Mon, Jan 28, 2019, 9:10 PM UTC

methodover wrote: post #42

gambler wrote: post #23

Earlier quoted context omitted.

Can you provide some links?

LeelaChess is one example for Chess. https://github.com/LeelaChessZero/lczero

This project actually proves the point of the root comment. The community spent tons of time on tuning/training this network, and it still routinely loses to Stockfish, which runs on inferior hardware. It illustrates that:

1. Deep mind kept a lot of information about their methods undisclosed.

2. Despite all the claims of generality, the algorithm requires insane amounts of fiddling to train. Just read their blog.

3. The hype around AlphaZero crushing every other algorithm in chess is overblown. It's competitive, but not clearly superior.

Still, Kudos to people running Lela project for doing what DeepMind should have done - describing how things really work and testing in real-life conditions.