Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

deepmind.com

Post reply on HN
Print view View original

301–310 of 459 posts

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#301

Post by slphil »

saberience wrote: post #238
derefr wrote: post #220

Earlier quoted context omitted.

I said "deep net" for a reason. A DNN model almost always turns out to be far, far smaller than the training data that was used to create it. For one example: any smartphone's face-recognition feature. Each such feature is a DNN which took millions of hours of face data to train... but the resultant model fits on an ASIC. Our DNA doesn't directly encode such a model, but it encodes a particular morphogenic chemical g…

Our DNA is NOT a trained deep net, nor is it a deep net period. Our DNA is a string of proteins which encode other proteins which gives the series of tasks needed to create and operate all the structures of the brain and body. The "training" of our deep net happens during our lifetime. We are not born with a trained deep net so your analogy that somehow we are born with a highly capable deep-net encoded into 1.6GB of…

You are willfully missing the point. Animals have instincts. The complexity of humans does not make them an exception to this rule. There are in fact large amounts of brain function that are baked in at birth (or developed in a predictable timeline after birth -- humans are basically born premature). Humans are able to instinctively perform behaviors which are not taught, although the majority of critical behaviors in humans are socially learned. Feral children (like Genie) are functioning organisms with complex behaviors. They're just defective humans because humans rely on a distributed learning system called culture in order to do the work that biology cannot.

You are insisting that because humans do not have instincts at a certain level of abstraction (playing video games) that no part of these instinctive brain functions play a role in the development of skill at Starcraft. This is wrong. Abstract reasoning is not simply learned, but it is HONED by experience and neural development. An AI has to do an enormous amount of work in order to replicate functions that humans can already do. This is the basic visual problem in AI that stumped researchers in the 60s who thought that tasks like visual recognition, spatial rotation, etc would be trivial because they are trivial to evolved organisms.

You're relying on some kind of mental model where brains are just masses of neurons that form all of their connections and complexity after birth. This is ultimately a political idea, and it's wrong. No neuroscientist believes this. Brains have pre-defined areas (with fuzzy borders) and many behaviors do come baked into the template. Complex behaviors like language do not, perhaps, although even there, the underlying functionality that permits language is an evolved trait (which is why other animals can't learn language). Research the FOXP2 gene, as just an obvious example.

Edit: Your post contains "structures of the brain". What exactly do you think the structures of the brain are, if not evolved modular solutions to complex problems? Your visual center is somewhat trained after birth, but it already exists. The same goes for speech, motor control, and all of the other unconscious or semi-conscious processes that all humans (and other animals as appropriate) share.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#302

Post by confiscate »

freeflight wrote: post #162
sl1ck731 wrote: post #137

Earlier quoted context omitted.

The purpose of limiting speed isn't to make an interesting contest, it is to accurately compare the "math" instead of the speed the math is done at. It isn't surprising that its fast, the surprising part is that it can make human-like decisions. The only way to compare whether its thinking is human-like is to restrain it from "brute forcing" the contest through speed. The model has likely learned that the faster it d…

But isn't the competency of a Starcraft player is also measured on his/her speed? In that context, you can't really measure strategy without accounting for timing/speed because a lot of tactics and strategies only become viable once the player has the required speed to actually realize them aka "micro".

yes but the ultimate goal, is to make an AI as "smart", or "smarter" than a human. That's why they keep making AI's play against human players in Chess, Go etc. It's not to prove computers are faster than humans. It's to prove computers can be smart like humans.

They want to make an AI that can teach new ideas to humans. New strategies that human bodies are physically capable of executing, but no human was "smart enough" to think of yet. An example is when the AI built a high number of probes at the start. That's "smart".

The only way to train an AI to be able to come up with new ideas, is to force it to be "slow". Otherwise, it will just always do the easiest way to win, which is out-micro. There is nothing interesting about a game like that. That only shows the AI is fast, but it won't be clear that it's "smart"

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#303

Post by dlubarov »

gamegoblin wrote: post #255
a_wild_dandan wrote: post #241

Earlier quoted context omitted.

Here's a graph of AlphaStar's APM versus a professional player's: https://i.imgur.com/TXeLkQK.png Evidently AlphaStar also has a similar Economy of Attention (where the player focuses) to a professional player, at around 30 screens per minute. Additionally, AlphaStar's reaction time is around 350ms, a significant disadvantage over a pro. The skepticism in this thread is absolutely justified but I think it's important…

I watched all of the event live and I feel that that graph is deceptive. If a game is 15 minutes and has 3 main battles lasting 15 seconds each, and you use 100 average APM on non-battle time and 1000 APM during battles, your average APM will be 145 but you obviously have a superhuman advantage. This is compounded by the fact that almost all of AlphaStar’s actions are “useful” whereas a significant amount of the huma…

TLO seems to have a longer tail than AlphaStar in that graph though, so doesn't that imply that TLO peaked at an even higher APM, presumably during battles?

Fair point about humans needing minor adjustments though. Another comment also mentioned a bug in the APM measurement: https://news.ycombinator.com/item?id=18994350

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#304

Post by ionforce »

dev_dull wrote: post #292

Here’s the question I have. Will it consistently beat the top player over and over? I see so much brittleness in AI such as this. Humans are much less prone to “bugs”. In an evolutionary adversarial environment, the human brain invariably comes out on top.

That's not fair. Humans are incredibly fallible. Humans tire, demand food, need to sleep, get bored. An AI just needs a graphics card and electricity.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#305

Post by jgrowl »

I wonder how useful ai will be in balancing games in the future. Games with more than one race and multiple upgrade paths seems like a nightmare to ensure that things are even for players that are equally skilled.

It would be interesting to have a game that would auto-balance itself, especially if you wanted to add extra content without having to worry about throwing everything off.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#306

Post by intuitionist »

Ar-Curunir wrote: post #242
derefr wrote: post #223

Earlier quoted context omitted.

True. Humans are pretty unique in that regard, though; pretty much no other animal is like that. It's easier to understand human neonatal development if you just considering all humans to be born premature. (It'd be really interesting to know whether that's literally true—whether keeping a human baby in the womb for an extra few months would actually result in the same stages of mental development being passed that o…

I've read somewhere that we are basically born prematurely (as you said) because if we waited any longer then our enlarged head sizes would make delivery quite possibly fatal.

My brother was born a week or so after his due date; they induced labor for him for exactly this reason. Perhaps unsurprisingly, his head circumference was literally off the charts.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#307

Post by sytelus »

rcheu wrote: post #46

This is really impressive, I didn't expect starcraft to be played this well by a machine learning based AI. I'm excited to read the paper when it comes out! That said, I'm not sure I agree that it was winning mainly due to better decision making. For context, I've been ranked in the top 0.1% of players and beaten pros in Starcraft 2, and also work as a machine learning engineer. The stalker micro in particular looked…

Also these wins are not using same inputs that human receive (ie on screen image) and outputs that humans are allowed. They instead use PySC APIs which has much more flexibility, perfect information and no constraints of limited screen real estate and pixels. There is a claim in that article that they have another version being trained that uses on screen only information but I still don’t know if AI is allowed to bypass the physical constraints of controller. So if AI has access to super human controller you will see AI performing super human actions like many commentators have described here.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#308

Post by anabis »

alasdair_ wrote: post #232

What are the games that, so far, still look like they will be too difficult for ML to play them at the highest level? I know Go was held to be this kind of game for a long time and is now close to being dominated by AI. Magic: the gathering perhaps?

non zero-sum games seems like a logical next step.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#309

Post by intuitionist »

cdelsolar wrote: post #273
CydeWeys wrote: post #97

Earlier quoted context omitted.

You play the game as it's written. Come back with another version of StarCraft that isn't so micro-intensive and we can see how the AI does on that. Chess and Go don't have any form of micro and AIs are nevertheless dominant there. I'd say, give AI development another year and I wouldn't expect there to be any kind of game, in any genre, that humans can beat AIs at. Whether it's Chess, Go, other classical board games…

except Scrabble

I assume you’re joking, but just in case you aren’t, Scrabble bots have outperformed top humans for 20 years with little more than a basic Monte Carlo tree search.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#310

Post by sytelus »

theflork wrote: post #234
dx87 wrote: post #181

Earlier quoted context omitted.

Another advantage was that the AI is just reading the game state through an API, it doesn't have to look on the screen. The game can be difficult to watch from a pro's perspective since they have to constantly click around the map to see what's happening, but the AI has perfect knowledge of everything it is capable of seeing, all without having to physically move a mouse to click on the screen.

Is the bit about reading the game through an api true? Earlier iterations of this same rl based agent that played Atari games would read just raw pixels not an api.

Yes, it’s true. A special PySC interface was created for AI. Also, it’s not only that AI doesn’t need to parse information available on much limited screen real estate but also that AI doesn’t have to use controller that have physical constraints. So AI has access to this super human controller and it can decide to click on one screen extreme and then another within 200ms.
Post reply on HN