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

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

deepmind.com

Post reply on HN
Print view View original

321–330 of 344 posts

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

#321

Post by rfrank »

ktRolster wrote: post #317
rfrank wrote: post #209

Earlier quoted context omitted.

When I was playing SC2 frequently a few years ago, someone made a program that used genetic algorithms to construct build orders [1]. It would produce a build that technically worked, but in a lot of cases they weren't very viable. I tried to make a blink stalker rush that'd be the rough equivalent of the build shown in the post liked above, just with the Protoss race in the game. The program would tell me to do thin…

The program would tell me to do things like make two extractors but put fewer than necessary probes on them, pull probes to extractors after X trips or at X time (can't remember which), Pros actually do both of those things.

This is true. I was on the higher end of the SC2 ladder (diamond 1v1) and still couldn't execute it consistently. One of many reasons I'm not a pro :)

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

#322

Post by Barrin92 »

__s wrote: post #301
Barrin92 wrote: post #278

Earlier quoted context omitted.

>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)

Yes, people play silly moves once in two decades, but again, in 99.9% of games nobody swindles or plays a6. In starcraft a good third of pro games or something involves cheesy openings.

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

#323

Post by mzw_mzw »

pmyjavec wrote: post #262
dguaraglia wrote: post #26

Earlier quoted context omitted.

How is 'saying no' going to stop the military of this or any other country from doing it? How do you measure the disadvantage we'd be at by not allowing our military to do it, but letting other militaries (over which we have no control) do it? Having a spine has nothing to do with it.

So, basically another arms race to the bottom, similar to nuclear warheads ? 1940s thinking with 2016 technology. I hear what you're saying but not all progress is good progress. The limits of our ability to think a global scale are an issue, we still have a tribe mentality, this discussion demonstrates that. "The Chinese, The British etc" We still think in terms of tribes, but we have technology change the world. Un…

How do you plan to convince China and Russia to stop worrying about weaponry and thinking in terms of tribes?

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

#324

Post by DonaldFisk »

theptip wrote: post #122

This is pretty interesting. DeepMind’s last triumph (beating the best human Go players with AlphaGo) is impressive, but Go is a great fit for neural networks as they stand today; it’s stateless, so you can fully evaluate your position based on the state of the board at a given turn. That’s not a good fit for most real-world problems, where you have to remember something that happened in the past. E.g. the ‘fog of war…

> it’s stateless, so you can fully evaluate your position based on the state of the board at a given turn.

That's not always true: https://en.wikipedia.org/wiki/Ko_fight

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

#325

Post by visarga »

taneq wrote: post #311
visarga wrote: post #282

Earlier quoted context omitted.

> Once you can launch an invasion without losing any soldiers, war seems like a much less dangerous proposition. Yes, but how can you stop everyone else from doing the same, if the AI part will be trivial to replicate?

Once one group has an AI capable of managing a drone army in near-optimal fashion, there won't be an 'everyone else'.

It's already done, the military is already killing people with AI driven drones.

Even hobbyists can 3D print drones and jet engines (really, check YouTube). The AI needed to fly a plane is much less than the one to drive a car.

[for reference] https://www.youtube.com/watch?v=7YcM6E_rg3A

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

#326

Post by oelmekki »

kurthr wrote: post #73
doikor wrote: post #42

Earlier quoted context omitted.

Is it harder to make an AI that is mediocre at playing the game vs one that is good? That is the main issue with making good AIs for games now. We want AIs (if you can call them that) that play kinda like humans but worse then the player as the player wants to win. Making an AI for game isn't about making a good AI. It is about making an AI that loses in a convincing manner. This is especially try for games like Star…

I think it's really important to realize is that a game AI isn't really there to try to win, or maybe even to "convincingly" beat you the same way a human is. Perhaps you could train an AI to make the game more "fun", but that's pretty hard to measure and people are so different. It's a really hard optimization process. One commonality, it seems, is that players want to get better at the game. Perhaps, an AI that TEA…

> Perhaps you could train an AI to make the game more "fun"

This is actually a way more interesting problem to solve, for the gaming industry.

Beating games is cool for industries where gaming is not the final problem (autonomous cars, various decision making, etc). But if AIs are to be exploited by gaming industry, it needs to learn things like : "is the user bored?", "what usually triggers new interest?", "how should difficulty be adjusted given current way the user is playing?", etc.

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

#327

Post by lenocinor »

formula1 wrote: post #176
cableshaft wrote: post #114

Earlier quoted context omitted.

I've been to the Game Developer's Conference (once) before. Believe me, there have been startups that have provided A.I. services for years (it was kind of like the equivalent of the Havok engine for physics, you had to implement it into your game). I don't know how well used they are, but I remember them being mentioned at one of the lectures about A.I. that I attended. They had tables and swag, too. I don't remembe…

Thats really interesting. Im curious why they havent been more popular. Were they heavilly focused on fps's?

There are a lot of problems, but mainly I think it boils down to game people, like a lot of programmers, wanting to write something themselves. You'll always understand it better, and it'll be perfectly tailored to your problem. Unless the problem is REALLY hard and takes a long time coding tedious things, they'd rather just do it themselves, since coding something is always more fun than figuring out someone else's code.

Also, out of my experience with many different fields of programming, game programmers seem to want to write more of the stuff themselves than most. This would be another huge subject to go into, but I think the biggest reason is that historically you couldn't ever really punt on performance in games, and you had to tweak everything to your problem. If your game ran slowly or looked bad, people just wouldn't buy it.

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

#328

Post by daveguy »

deepnotderp wrote: post #271

By the ways, if anyone's interested, there was a deluge of deep learning papers today and one of them basically used deep learning to make deep learning models and it did better than humans.

Seriously... Source? I have looked at new papers indexed by Google scholar and I don't see anything that boasts this. It would be the feature of the abstract and would probably be a Nature/Science paper. So... Source??

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

#329

Post by dguaraglia »

pmyjavec wrote: post #262
dguaraglia wrote: post #26

Earlier quoted context omitted.

How is 'saying no' going to stop the military of this or any other country from doing it? How do you measure the disadvantage we'd be at by not allowing our military to do it, but letting other militaries (over which we have no control) do it? Having a spine has nothing to do with it.

So, basically another arms race to the bottom, similar to nuclear warheads ? 1940s thinking with 2016 technology. I hear what you're saying but not all progress is good progress. The limits of our ability to think a global scale are an issue, we still have a tribe mentality, this discussion demonstrates that. "The Chinese, The British etc" We still think in terms of tribes, but we have technology change the world. Un…

I get it, and I wholeheartedly support your position on the issue. The reality, unfortunately, is that we are horrid little creatures always scheming and fighting for power. Stopping nation X from doing, will only encourage nations Y and Z to develop it faster as an advantage.

The only way I can see an agreement to limit the escalation of AI warfare is on the same context we saw the START treaty: once the weapons are developed by at least two key players as "deterrent" there's an incentive to reach an agreement to stop further development.

Call me cynical, but if this election has shown me anything is how tiny-minded people still command an inordinate amount of power in this country.

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

#330

Post by ktRolster »

rfrank wrote: post #321
ktRolster wrote: post #317

Earlier quoted context omitted.

The program would tell me to do things like make two extractors but put fewer than necessary probes on them, pull probes to extractors after X trips or at X time (can't remember which), Pros actually do both of those things.

This is true. I was on the higher end of the SC2 ladder (diamond 1v1) and still couldn't execute it consistently. One of many reasons I'm not a pro :)

One thing that helps (fwiw) is to recognize a diagnostic.....for example, if at minute 4 you are unable to build a gateway, it means you messed up the probe count at minute 2. That gives you almost immediate feedback on where the problem happened, without having to watch the replay.
Post reply on HN