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

191–200 of 459 posts

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

#191

Post by vertline3 »

arcticfox wrote: post #166
taneq wrote: post #144

Earlier quoted context omitted.

How many of those 500 actions are actually useful? I haven't watched competitive StarCraft games for years but back when I did, rates were more like 300APM and even then the players basically spam clicked the background or selected random units non-stop and were probably only doing 50-100 actual effective actions.

> How many of those 500 actions are actually useful? Exactly, a human doing 500 APM during intense moments is going to be way different than an AI bursting 1000 APM with pixel-precision during the most crucial moment in a game. TLO spent a ton of time at >1000 APM and walked his army directly into enemy shots all the time. MaNa had much better control at ~400 APM. So APM is really irrelevant to control - for humans.…

Such high actions per minute does not seem fun to me, and possibly a repetitive strain injury waiting to happen.

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

#192

Post by dmoy »

vertline3 wrote: post #191
arcticfox wrote: post #166

Earlier quoted context omitted.

> How many of those 500 actions are actually useful? Exactly, a human doing 500 APM during intense moments is going to be way different than an AI bursting 1000 APM with pixel-precision during the most crucial moment in a game. TLO spent a ton of time at >1000 APM and walked his army directly into enemy shots all the time. MaNa had much better control at ~400 APM. So APM is really irrelevant to control - for humans.…

Such high actions per minute does not seem fun to me, and possibly a repetitive strain injury waiting to happen.

It is why I stopped playing SC, and I was never any good anyways. Still fun, but it just hurt real bad.

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

#193

Post by 59nadir »

Thaxll wrote: post #114
knicholes wrote: post #85

Earlier quoted context omitted.

This is how it responds to cannon rush. : ) https://www.youtube.com/watch?v=vYdWQjTWTFM

This is not how a player would do a cannon rush, it needs to be hidden / at the edge of the opponent view.

That's inaccurate. The best cannon rushers generally build them visibly, but not just anywhere. If you look at someone like QuasarPrintf as an example, a player that keeps a fairly high rank on an account that literally only cannon rushes (there is no anonymity, no pretense about what's going to happen), he wins despite people knowing what's going to happen and putting the cannons mostly well in view of opponents on a lot of maps.

Printf is part of a fairly small group of cannon rushers that don't simply see it as just another cheese, because what generally defines a cheese strat is that it can be easily countered if you know it's coming; not so with their cannon rushes.

Now, with that said, Printf (or any other "I always cannon rush" player aren't winning tournaments), but that's partly because not many players decide that they want to stake their development on any one strat like that, and if they do, it'll likely be one that's deemed more legitimate by the community.

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

#194

Post by biohazardpb4 »

ehsankia wrote: post #165
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…

> While they have similar APM to SC2 pros Wasn't the APM closer to half that of the pros? https://storage.googleapis.com/deepmind-live-cms/images/SCII...

There's a tail which shows that a small number of AlphaStar minutes had > 1k actions.

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

#195

Post by thomasfortes »

asdfasgasdgasdg wrote: post #189
jgon wrote: post #150

Earlier quoted context omitted.

Even the 200ms reaction time seemed overly slanted towards the AI. I don't think that is the actual reaction time of top pros, in the matches the AI played the human player would teleport in from complete invisibility and try to use an instant cast spell and the AI would have already teleported out. Yes the theoretically may have been constrained to a 200ms reaction time, but in practice the AI was playing at a super…

The game is difficult to watch, but does anyone honestly believe that an AI is going to have a difficult time parsing the scene if it is trained to do so? That to me just seems like a question of resources. We're pretty good at image recognition and segmentation now, and that's without the unlimited amounts of training data one could generate when using a controlled game environment with a limited range of possible a…

But on the other hand, an AI that beats humans using brute force in a game where it makes a ton of difference isn't much fair too.

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

#196

Post by dooglius »

derefr wrote: post #146
Cookingboy wrote: post #113

Earlier quoted context omitted.

The results are obviously impressive, but even then there is a lot of work to do as far as learning efficiency goes: "The AlphaStar league was run for 14 days, using 16 TPUs for each agent. During training, each agent experienced up to 200 years of real-time StarCraft play. " MaNa probably played less than 2-3 years of Starcraft in his whole life (by that I mean 24hr x 365d x 3), and was learning with a much less foc…

Another way to think about it is that a human brain is mostly doing transfer-learning, on top of a 99%-baked deep net that was wired up during foetal development from our DNA, where that DNA-persisted model has "seen" hundreds of millions of years of training data. Humans don't have to learn to process, recognize, and classify objects in visual sense-data, for example. We can do that from the moment we're born, becau…

Is there evidence for this? My mental model has been that DNA encodes more along the lines of hyperparameters: amount of gray matter vs white matter, locations of brain regions and folds, etc, but the connections between neurons, and their weights, were all learned. There isn't that much information you can stuff into DNA, after all.

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

#197

Post by nardi »

hughzhang wrote: post #98
Thaxll wrote: post #59

Earlier quoted context omitted.

This is exactly what I think, I'd like to see how Alphastar react to "cannon rush" or other weird bo where you need to be "smart" to counter it and just not be based on insane / none human micro.

AlphaStar makes up for its slightly subpar macro with REALLY good at micro. Thus, more micro heavy counters like cheeses are unlikely to beat it.

The strategies might be subpar, but the economy sure isn’t. It consistently had better economy.

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

#198

Post by b_tterc_p »

porpoisely wrote: post #141
jonahx wrote: post #23

Does anyone know if this opens the door to using these techniques for poker (given that they've now show success on games of imperfect information)? Thus far the solutions to poker have involved solving the game tree through raw computational power and clever methods of information collapsing: http://science.sciencemag.org/content/347/6218/145 But it seems the techniques used here might be both far more efficient, as…

And to add that, what if deepmind could get a poker history of the players at the table to create a poker profile of each player it is playing against. Having a percentage of a player's likelihood of folding and bluffing could keep it an advantage over a purely objective game theory aspect of the game. Maybe a certain player is more likely to bluff 5 hours into a game based off of player history analysis. Going furth…

deepmind is not necessary for that and also probably wouldn’t work.

If you have player history you can construct perfect models for their playing habits and even update it as time goes on like a multi armed bandit problem. This can be simple probability heuristics and an optimization function.

The problem with it is that the machine becomes biased to past results. Top human players are good because they adapt. I would put my money on the humans

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

#199

Post by pesmhey »

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…

In a nutshell, AI micro was flawless, makes up for suboptimal macro?

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

#200

Post by aurelwu »

vertline3 wrote: post #191
arcticfox wrote: post #166

Earlier quoted context omitted.

> How many of those 500 actions are actually useful? Exactly, a human doing 500 APM during intense moments is going to be way different than an AI bursting 1000 APM with pixel-precision during the most crucial moment in a game. TLO spent a ton of time at >1000 APM and walked his army directly into enemy shots all the time. MaNa had much better control at ~400 APM. So APM is really irrelevant to control - for humans.…

Such high actions per minute does not seem fun to me, and possibly a repetitive strain injury waiting to happen.

the 1000 apm thing is because of a bug in how apm is calculated in starcraft2. There is a hotkey to assign all your units to a new control group while also deleting it from all other control groups which TLO extensively uses, and while it just is one key-combination to press it records as 1 action per unit which was selected. The real APM of pro players averages at 250-400 and peaks at 600-700.
Post reply on HN