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

341–350 of 459 posts

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

#341

Post by Etheryte »

forax wrote: post #311
jgrowl wrote: post #305

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.

That's a cool idea but many games already struggle to find a fair balance point at all ranges of human skill, so expanding that range to include AI could just make things more difficult. Maybe there's a way to force the AI to replicate bad players, but I'm not sure what learning objective you would give it to achieve that.

I think achieving suboptimal play can be pretty straightforward — keep the parameters the same, but simply limit the amount learning. Some tweaks might be necessary here and there, but as long as you have basic gameplay down but not perfected, it should work pretty well.

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

#342

Post by glun »

skwb wrote: post #337
forax wrote: post #311

Earlier quoted context omitted.

That's a cool idea but many games already struggle to find a fair balance point at all ranges of human skill, so expanding that range to include AI could just make things more difficult. Maybe there's a way to force the AI to replicate bad players, but I'm not sure what learning objective you would give it to achieve that.

I don't follow gaming balancing too closely, but I (naively) assume there's some reasonable analytical solution to find tuning. Like I would imagine if you're Blizzard and have logs of all the data, you could just regress race attack/defense/movement/etc. stats to find a potential equivalence point. I suppose there's lots of interactions, but finding "well Zerg beats Protoss X% of the time", you could balance by mess…

Starcraft is generally balanced by adjusting the map pool rather than the races.

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

#343

Post by feanaro »

maksimum wrote: post #319
confiscate wrote: post #275

Earlier quoted context omitted.

Yes I am curious of this too. What happens if the human has a giant TV screen that can see the whole map at once Or, what if we slow down the game, so that the human can actually pause the game each second and consider what to do next. That's basically what the computer is allowed to do

> Or, what if we slow down the game, so that the human can actually pause the game each second and consider what to do next. That's basically what the computer is allowed to do While this would make it more fair, it would just make the micro game more similar to chess or go. I don't think humans would necessarily win in the end.

That's a good insight and yes, humans would probably be overpowered eventually. However, this is just the consequence of the fact that all games are similar if you remove external limitations such as reaction time (or, alternatively, produce a more efficient "being" which is not as subject to these limitations as some other).

Starcraft is like chess in some sense. The largest fundamental difference is that it isn't a perfect information game.

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

#344

Post by eecsninja »

How I would summarize the development of AlphaStar and Mana's strategy over the series:

1. AS studies games played by humans to learn what they do. 2. AS takes advantage of high-APM, high-precision blink stalker micro to defeat immortals (something no human can cognitively/mechanically accomplish). 3. Mana realizes he cannot play vs AS as if he were playing vs a human. 4. Mana discovers an AI exploit using the warp prism + immortals to force AS's army back, keeping his own base safe. This is a specific counter-AI strategy, not something that would have worked vs a human player. AS does not know how to properly react because it has not seen any replays of humans going up against an AI by exploiting it. 5. Mana gets enough breathing room to build up a large enough force to win the game.

In short, Mana won because he "solved the problem" of how to exploit this particular AI.

This is actually not a new strategy -- several years back, the stock SC2 AI would do the same thing: pull back when you attacked its base. I could win vs AI using the exact same trick that Mana used. Blizzard has since updated the AI not to fall for this trick.

The real test of DeepMind's learning abilities is thus: if AlphaStar had seen replays of that exploit vs AI, along with all other replays of humans vs AI over the years, would Mana still have been able to win?

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

#345

Post by feanaro »

kaveh_h wrote: post #297
asdfasgasdgasdg wrote: post #189

Earlier quoted context omitted.

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…

For real life applications, parsing the ”scene” would have impact as it could only convey imperfect information retained. In the game of starcraft the information is perfect when fog of war have been removed this together with unlimited attention (camera viewport) helps action potential and macro planning. No player is ever going to be able to consider precise strategy on the whole map perfectly in their mind. If dee…

There is another potential use: given these limitations, an AI might be able to learn to be better strategically, which could translate to an even greater advantage once the limitations were removed later on.

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

#346

Post by glun »

ForrestN wrote: post #73

Can anyone who has a full context compare this to OpenAI's work on Dota 2? Which is more impressive, both in how far along it is and the relative game difficulty?

Dota is a much harder game strategically, in Starcraft it's easier to compensate with mechanical skill. You can see this in the results. The Dota ai played a very dumbed down version of the game and still got trashed by the pros.

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

#347

Post by erikb »

kriro wrote: post #339

First Go, now Starcraft 2...I fully expect archery or women's golf to be conquered next. Someone at deepmind must have an axe to grind with Korea ;)

This is more about historical AI challenges. When Chess was beat people realized painfully and happily that they can't beat Go with the same approach. Therefore it was the new Mount Everest.

And Starcraft is a competition because SC1 was a game that was easily adaptable for AI hobby coders and competitions. A little like they have this Robo Soccer world championship for Robo builders. It's part of the domain culture I guess.

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

#348

Post by erikb »

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…

I think the bigger point in the future will be not AI beating known gambling activities (gambling in the sense that you put in money and have a random outcome about whether you get money back, let's not have a discussion about poker being gambling or competitive sport). The bigger point will be AI creating gambling activities that are even less resistable than our existing options. There might be digital drugs.

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

#350

Post by richardknop »

mithr wrote: post #298
kzrdude wrote: post #80

Earlier quoted context omitted.

Perfect micro bots don't excite me much, because they've existed all along, and it's not an AI task.

The interesting part to me is that, as far as I understand, the AI figured out this strategy by itself, basically deciding that it would be a good way for it to win games, rather than being specifically programmed to do it. That's actually pretty cool! Other than that, I agree, and am also much more interested in what happens when you have a more level playing field (using camera movement rather than API, limiting re…

Not really. The version which learned from scratch was scrapped as it didn’t work at all. This version learned by observing pros. So it didn’t learn by itself, it imitated and perfected pro players.
Post reply on HN