DeepMind and Blizzard to release StarCraft II as an AI research environment • Hacker News Board

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#301

Post by __s » Sat, Nov 05, 2016, 11:17 AM UTC

Barrin92 wrote: post #278

seanwilson wrote: post #248

Earlier quoted context omitted.

> Similar things weren't really said about Go or Chess. Both are perfect information games so, by definition, they can't involve deceit I took deceit to mean tricking your opponent into thinking you were doing one thing when you were actually going to do another. You can't do that in Go or Chess? What I generally meant was maybe there's some really boring numerical number crunching or some simple mechanical algorithm…

>I took deceit to mean tricking your opponent into thinking you were doing one thing when you were actually going to do another. You can't do that in Go or Chess? Well you can technically but it's horrible. No above amateur player tries to play 'trick moves'. Skilled players try to find the objectively best moves in the given position because tricks are just way to easily spotted. The "betcha didn't see that coming!"…

Caveat for picking openings to get out of your opponent's book

Karpov playing black, throws opponent off with 1 ..a6 http://www.chessgames.com/perl/chessgame?gid=1068157

Also, good players seek to not lose lost games https://en.wikipedia.org/wiki/Swindle_(chess)

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#302

Post by pinouchon » Sat, Nov 05, 2016, 11:19 AM UTC

seanwilson wrote: post #248

jdoliner wrote: post #239

Earlier quoted context omitted.

Similar things weren't really said about Go or Chess. Both are perfect information games so, by definition, they can't involve deceit There's no need to try to detect subtle patterns in your opponents behavior because you have the entire game in front of you. That's not to say it's impossible but they do very much have their work cut out for them. It's an entirely different type of game that is much more difficult th…

> Similar things weren't really said about Go or Chess. Both are perfect information games so, by definition, they can't involve deceit I took deceit to mean tricking your opponent into thinking you were doing one thing when you were actually going to do another. You can't do that in Go or Chess? What I generally meant was maybe there's some really boring numerical number crunching or some simple mechanical algorithm…

At the highest levels, a surprised opponent is a dead opponent.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#303

Post by pinouchon » Sat, Nov 05, 2016, 11:25 AM UTC

seanwilson wrote: post #235

rezashirazian wrote: post #214

If DeepMind is planning on building an AI that can beat the best human SCII player, they have their work cut out for them. I'm not sure how familiar people are with StarCraft II, but at the highest levels of the game, where player have mastered the mechanics, it's a mind game fueled by deceit, sophisticated and malleable planning, detecting subtle patterns (having a good gut feeling on what's going on) and on the pro…

> I'm not sure how familiar people are with StarCraft II, but at the highest levels of the game, where player have mastered the mechanics, it's a mind game fueled by deceit, sophisticated and malleable planning, detecting subtle patterns (having a good gut feeling on what's going on) and on the pro scene knowledge of your opponent's style. I wouldn't be surprised if an AI comes along that shows this human perception…

Top players go to great lengths to just deny scouting information (for example killing inoffensive hallucinated phoenixes flying their way) just to keep their opponent in the dark.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#304

Post by gspetr » Sat, Nov 05, 2016, 11:33 AM UTC

keerthiko wrote: post #291

shannonpig wrote: post #285

Earlier quoted context omitted.

I think you're thinking about the difference between full information games vs partial information games, rather than stateless games (the state of a starcraft game is stored on a central server, the computer just has no access to it). There's already been excellent progress in poker AI based on traditional game theory, see http://poker.cs.ualberta.ca/ .

It's not just the limited information space, however. There's also the solution space or "action space". A poker game-space is quite narrow compared to that of StarCraft because of pixel-wise differences. This is the main reason that makes StarCraft "much more realistic". In real life you have infinite moves and options with (almost) analog differences, whereas a game like Poker is much more discrete. Go is somewhere…

> but it needs to learn the relevance of such pixel-sized mistakes, which is unlikely to have as much of an impact in a poker game or Go game as it would in StarCraft.

I agree with your point, but you need to look no further than the game that AlphaGo lost against Lee Sedol.

It committed a very bizarre mistake that made no sense gamewise.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#305

Post by halflings » Sat, Nov 05, 2016, 11:54 AM UTC

tempestn wrote: post #297

halflings wrote: post #270

Earlier quoted context omitted.

I do not understand the point of an AI if you want it to be equal in all ways to a human. Why not just fight a human? The goal is to build an AI that is at least as good as pro players (which would involve building models and technology capable of taking complex decisions etc.). The goal was never to implement something that is strictly equal to a human. You cannot blame the AI for having a better memory and perfect…

I agree with you. As I said, > Your parent post appears to suggest mitigating these other advantages in various ways (although I don't personally agree with that approach, since the computer isn't doing something that's out of reach for humans, just things that aren't practical for humans to achieve consistently). As far as your last paragraph, I suspect the issue is that people building AIs generally try to follow t…

I don't think it's as easy as that. Even with perfect macro + micro, your opponent could simply scout you, see what build you're going for, and counter your build.

Pro players do have (quasi-)perfect macro: They build units and buildings exactly when they should be built (especially at the early stages of the game). They also have an excellent micro. What makes one player win against the other is often the choices they make (going for a surprising build, or simply executing an attack in a way their opponent wouldn't be ready for).

So I'm pretty sure an AI that would just mass zerglings and micro them "perfectly" still would be crushed by decent players that know how to counter that rush. (build a wall, and have siege tanks or a similar unit)

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#306

Post by halflings » Sat, Nov 05, 2016, 11:58 AM UTC

TeMPOraL wrote: post #300

halflings wrote: post #270

Earlier quoted context omitted.

I do not understand the point of an AI if you want it to be equal in all ways to a human. Why not just fight a human? The goal is to build an AI that is at least as good as pro players (which would involve building models and technology capable of taking complex decisions etc.). The goal was never to implement something that is strictly equal to a human. You cannot blame the AI for having a better memory and perfect…

> I do not understand the point of an AI if you want it to be equal in all ways to a human. Why not just fight a human? Well, if you want just an AI to win with humans, you can stick to playing chess - nowadays the AI can drunk-walk its way to victory through the game tree faster than humans can make leaps in strategic thinking. The point of such experiment here is to impose limits on what an AI can do in order to ca…

The examples you previously gave are different from what you're saying now, but like I said the article clearly said that they will limit the number of actions per minute which means: no gimmicky/weird micro tricks.

Any other advantage you mentioned (computers having a larger memory and faster reaction time than humans) shouldn't be removed, as that doesn't make any sense: machines will be machines. You're building an AI on such a complex game because you want to be able to model hard problems with incomplete information, and to do so you do need to use a lot of memory and the computer's fast processing... even if that means being faster than a human. That is "fair".

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#307

Post by halflings » Sat, Nov 05, 2016, 12:05 PM UTC

thaumasiotes wrote: post #217

uw_rob wrote: post #116

Earlier quoted context omitted.

That may be an ok definition for you, but it most certainly isn't for SC2. I wasn't anywhere near the pro level and I would peak at 300 apm and would spend most of the game around 200. 12 APM is borderline not playing.

Consider it a statement about what I'm looking for in a game. I'm not really interested in competing over who can work their mouse button harder, or in driving myself to excel in giving myself repetitive motion injuries. Those are things that take away from starcraft; they don't enhance it.

I would strongly encourage you to go against your preconceived idea of what StarCraft is (a game where people compete on who's the fastest to bash their keys) and see a professional game and all the strategy it entails, such as in the semi-finals and grand final that will be on today. Pro players do have valid reasons for having such a high APM (even if a portion of it, maybe 30%, is just "spamming" to keep theirselves active and ready), but you can be an excellent player with rather low APM (~120 maybe?). Why would you need to do 2 action per second? A lot of it is simply building units periodically (e.g pressing 1 then "S" every 10 seconds) but then APM really gets high when there is a battle and you need to give actions to multiple sets of units to get a good engagement.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#308

Post by halflings » Sat, Nov 05, 2016, 12:07 PM UTC

xg15 wrote: post #165

I applaud the idea, but I'm worried about how open the results of the research will be in the end. I think the worst possible outcome for society would be if we ended up with capable AI but with the algorithms only accessible for a handful "AI-as-a-service" companies. The second concern is understandability of the algorithms: from what I've read, it's already hard to deduce "why" an ANN in a traditional problem behav…

DeepMind always published papers about their research (the AlphaGo paper goes into a lot of details on how everything works). Not sure why you're doubting the openness of this initiative when they are pushing an open API for everybody to do research on, not just DeepMind.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#309

Post by ygra » Sat, Nov 05, 2016, 12:09 PM UTC

Houshalter wrote: post #227

clearf wrote: post #125

Earlier quoted context omitted.

I'm not sure that accuracy/HP are the right things to tweak. I've always wanted to be "surprised," in an unscripted way, by AI enemies in FPS and RTS games.

One game experimented with smart enemy units that could sneak up on a player and attack them from behind, or outflank them. The players hated it and assumed the computer was cheating and just spawning enemies behind them. The same is sort of true in RTS games. The new rerelease of age of empires 2 has vastly improved AI that was developed by modders. Lots of players thought it was just cheating. But in general it has…

For the vast majority of players it's probably irrelevant whether the AI cheats or not. The goal is not to play fair and beat the human usually, but to put up a good fight and make things challenging and, most importantly, fun for the human. Of course, competitive and professional players have different expectations or requirements in that regard.

Still, AI in games is mostly a trade-off. It usually can't take too much resources (because it usually has to run on the same machine the human is playing on), it has to be believable and fun to play against. This usually rules out too fancy algorithms and approaches with dubious returns.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#310

Post by dsjoerg » Sat, Nov 05, 2016, 12:18 PM UTC

rezashirazian wrote: post #214

If DeepMind is planning on building an AI that can beat the best human SCII player, they have their work cut out for them. I'm not sure how familiar people are with StarCraft II, but at the highest levels of the game, where player have mastered the mechanics, it's a mind game fueled by deceit, sophisticated and malleable planning, detecting subtle patterns (having a good gut feeling on what's going on) and on the pro…

They have their work cut out for them, but not in the way you think.

Remember that it's easy for an SC2 AI to beat a human if there are no constraints such as APM. So if and when the AI wins, the humans are going to complain that the constraints weren't set tightly enough.

So the contest is going to devolve into a war over the constraints to use, just like the endless bickering between Protoss Terran and Zerg about balancing the units.

The best thing DeepMind will be able to say is that they were able to beat Flash (or whoeever) with only 150 APM. But Flash will complain that it wasnt fair because DeepMind was able to be so efficient with those 150 APM so that really it should be limited to 100.

I suppose once the APM cap is well below what humans do, then the humans will have to admit a sort of defeat.

Hopefully there will be a ladder running where humans can play against the AIs under development and get a feeling for how they play. Will be really fun & interesting!