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

151–160 of 344 posts

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

#151

Post by Corence »

burke wrote: post #132
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…

> When Google’s AI can beat a human at StarCraft, it’s time to be very afraid. I don't actually agree with this. Unlike Go, StarCraft is not only a game of strategy; "micro" (micro-managed tactics, basically) also plays a big role. An AI is going to be able to issue a LOT more commands per second than even the most skilled humans, giving them a natural tactical advantage. Strategy is more difficult for an AI, but not…

The article says they're restricting the APM for the agent to try to reduce the impact of this.

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

#152

Post by cmdrfred »

scarmig wrote: post #137
burke wrote: post #132

Earlier quoted context omitted.

> When Google’s AI can beat a human at StarCraft, it’s time to be very afraid. I don't actually agree with this. Unlike Go, StarCraft is not only a game of strategy; "micro" (micro-managed tactics, basically) also plays a big role. An AI is going to be able to issue a LOT more commands per second than even the most skilled humans, giving them a natural tactical advantage. Strategy is more difficult for an AI, but not…

Isn't it easy to account for this? Just force the AI to stick to between 100 and 150 APM, and it becomes its responsibility budget its APM.

Depends on how you limit as well, what if it does 100 actions at once for example.

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

#154

Post by trjordan »

lordnacho wrote: post #139
arcticfox wrote: post #134

Earlier quoted context omitted.

I agree. I think you'd have to limit that machine's APM to somewhere around the human limit, and make it choose which actions it wants to spend its time on. Otherwise the AI is eventually just going to absolutely destroy humans with micro, which is not remotely interesting. We've known transistors were faster than fingers for ages.

> Otherwise the AI is eventually just going to absolutely destroy humans with micro, which is not remotely interesting. If you could issue as many orders as you wanted, what would the optimal strategy be?

A big part of Starcraft is that certain units counter other units. Tanks counter zerglings, because they do splash damage to a bunch of them at once.

Here's what you can do with infinite APM: https://www.youtube.com/watch?v=IKVFZ28ybQs

It's just broken. It's not even the same game.

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

#155

Post by Fang_ »

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…

>an AI that TEACHES the user to improve their play

Wouldn't you be able to do mutual training that way? By mutating the AI's "strategy" only after losses, the player would continuously need to figure out a weakness in the AI's game-plan. And the AI tries to evolve its strategy every time it loses.

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

#156

Post by tyrust »

lordnacho wrote: post #139
arcticfox wrote: post #134

Earlier quoted context omitted.

I agree. I think you'd have to limit that machine's APM to somewhere around the human limit, and make it choose which actions it wants to spend its time on. Otherwise the AI is eventually just going to absolutely destroy humans with micro, which is not remotely interesting. We've known transistors were faster than fingers for ages.

> Otherwise the AI is eventually just going to absolutely destroy humans with micro, which is not remotely interesting. If you could issue as many orders as you wanted, what would the optimal strategy be?

I haven't played SC in a few years, but I think I can give a basic answer.

There's would not be one optimal strategy, but many optimal strategies depending on the matchup between units. By taking advantages in differences in movement speed, attack range, attack projectile speed, and attack cooldown, a weaker group of units can potentially beat a stronger group.

This is an older video that demonstrates some examples of winning with good micro: https://youtu.be/CdSKD3LRHV8?t=11. An AI knowledgeable of and capable of executing such tactics would be pretty strong.

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

#157

Post by jensvdh »

cmdrfred wrote: post #152
scarmig wrote: post #137

Earlier quoted context omitted.

Isn't it easy to account for this? Just force the AI to stick to between 100 and 150 APM, and it becomes its responsibility budget its APM.

Depends on how you limit as well, what if it does 100 actions at once for example.

Perhaps we can have the AI move the mouse/keyboard at "human" limits?

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

#158

Post by ryukafalz »

burke wrote: post #148
scarmig wrote: post #137

Earlier quoted context omitted.

Isn't it easy to account for this? Just force the AI to stick to between 100 and 150 APM, and it becomes its responsibility budget its APM.

Sure, but even then it's difficult. Micro'ing three fronts at once would be difficult for a human but could easily fit within the AI's budget. You could solve this by coming up with some sort of context-switch effort function but it starts to feel forced. Or at least, once you start calibrating the parameters of the problem around human limitations, it sort of feels weird to talk about the computer being better or wo…

>You could solve this by coming up with some sort of context-switch effort function but it starts to feel forced.

Doesn't seem too forced to me IMO. Humans have to expend more effort to context switch, so if the goal is to put humans and computers on a level playing field that's something you have to take into account.

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

#159

Post by defen »

trjordan wrote: post #154
lordnacho wrote: post #139

Earlier quoted context omitted.

> Otherwise the AI is eventually just going to absolutely destroy humans with micro, which is not remotely interesting. If you could issue as many orders as you wanted, what would the optimal strategy be?

A big part of Starcraft is that certain units counter other units. Tanks counter zerglings, because they do splash damage to a bunch of them at once. Here's what you can do with infinite APM: https://www.youtube.com/watch?v=IKVFZ28ybQs It's just broken. It's not even the same game.

How does the AI "know" which Zergling is going to be fired upon? Are the tank shots not instant-hit? Or is this just a demonstration of what actual optimal control would look like.

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

#160

Post by patmcguire »

lordnacho wrote: post #139
arcticfox wrote: post #134

Earlier quoted context omitted.

I agree. I think you'd have to limit that machine's APM to somewhere around the human limit, and make it choose which actions it wants to spend its time on. Otherwise the AI is eventually just going to absolutely destroy humans with micro, which is not remotely interesting. We've known transistors were faster than fingers for ages.

> Otherwise the AI is eventually just going to absolutely destroy humans with micro, which is not remotely interesting. If you could issue as many orders as you wanted, what would the optimal strategy be?

There's almost certainly a bunch of timing-based micro with animations/game ticks/etc that a machine would find. For example, if a machine does a sequence of actions with sub-millisecond precision they can pop a unit into range, fire, and then pop back out again without being fired upon over and over.

A lot of units would be rendered useless because it's balanced for humans. That means the units they counter would be a lot stronger. I'm afraid it would probably just be a race to get the fastest rush.

Post reply on HN