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

DeepMind Challenges for StarCraft

gamasutra.com

Post reply on HN
Print view View original

41–50 of 137 posts

Re: DeepMind Challenges for StarCraft

#41

Post by scottjad »

Starcraft is a game that is played with mouse and keyboard (or game controller on console). I think in order to say an AI has beat a human, it should have to use the same interface that a human uses. That's part of the definition of the game.

In Go, anyone can place a stone as well as anyone else, it's deciding where to place a stone that's the game. In Starcraft, not everyone can control the interface to the game equally well. Playing Starcraft without using the same interface as humans is like playing baseball with something other than a baseball bat.

Also, I think it's unfortunate that they're choosing Starcraft 1: Brood War (presumably because of API reasons) instead of Starcraft 2, since there are many more top-level players playing sc2 right now to give it a run for its money, with an evolving meta that could more likely adapt and challenge the AI after it wins some matches. SC2 is where the tournaments and money is right now (compared to BW), hence the best players devoting the most time.

Re: DeepMind Challenges for StarCraft

#42

Post by bottled_poe »

forrestthewoods wrote: post #30

I want to see StarCraft next and then League of Legends/DOTA. The control advantage an AI has in StarCraft is immense. It exists in League of Legends, especially when perfectly coordinating 5 different characters, but it's less impactful.

The control required to master SC2 is far beyond any MOBA style game. AI for MOBA games seems trivial compared to AI for a large scale RTS. It's the difference between controlling 1 unit vs 100 units.

Re: DeepMind Challenges for StarCraft

#43

Post by im3w1l »

eru wrote: post #38
im3w1l wrote: post #31

Earlier quoted context omitted.

Wouldn't that depend on what you want to achieve? To maximize $/h you need to understand your opponents weaknesses and exploit them. But if you just to beat the best humans, and don't care about the margin with which you beat them, then playing a mathematically perfect game should be enough. And before you ask, a mathematically perfect game can incorporate occasional bluffs, and occasional calling of bluffs, this wou…

That's about it for a two player game. Anything with more than two people has more interesting / complicated properties.

One very real issue I'd imagine is that two players could cooperate out of ignorance, i.e. either player could do better by deceiving the other, but they are not good enough players to realize that.

Re: DeepMind Challenges for StarCraft

#44

Post by forrestthewoods »

bottled_poe wrote: post #42
forrestthewoods wrote: post #30

I want to see StarCraft next and then League of Legends/DOTA. The control advantage an AI has in StarCraft is immense. It exists in League of Legends, especially when perfectly coordinating 5 different characters, but it's less impactful.

The control required to master SC2 is far beyond any MOBA style game. AI for MOBA games seems trivial compared to AI for a large scale RTS. It's the difference between controlling 1 unit vs 100 units.

I don't think I agree with that at all. If you can control 1 unit it's trivial to control 100.

I might argue that the AI vs AI challenge in Starcraft is deeper and more difficult to master. But for AI vs Player the Starcraft AI has an enormous mechanical advantage. Being able to harass mineral lines in four different places is a big deal. Being able to perfectly micro multiple lines of attack/defense is a big deal. It's very unfair and very much in the AI's favor.

Chess In my moderately educated opinion.

Re: DeepMind Challenges for StarCraft

#46

Post by huac »

econnors wrote: post #13
fatman13gg wrote: post #5

It would also be interesting to see if DeepMind challenges Dota 2 one day maybe. How they would handle a 5-man team game and adapting to major game updates?

I'm more of a LoL guy, but i'd be excited to see this in action. I think it's actually an easier challenge than starcraft - the action space is much smaller and dodging/aiming AI already gives some players extreme advantages (against the TOS of course).

IMO the smaller action space/better defined win conditions is outweighed by the greater playstyle diversity: SC has 3 races while League and Dota have 100+ champions to understand the interactions with. How is an AI supposed to know that Tryndamere's ult has a 0.5 second cast time, but can't be interrupted by any CC?

Personally, I think (all else being equal) Dota might be an easier starting point than League because of its focus on item abilities, rather than champion abilities. Anybody can use a BKB in Dota, but in League you have Fiora W, Morg E, and a bunch of other things. You have a smaller set of abilities/effects to worry about.

The dodge/aim AI can be situationally good (Cass bots) but still, the best players do win against scripters. Scripters rarely make it into the elite echelons of the ladder; there's a situation right now with a former pro Korean player who started scripting but couldn't make it back into Master tier. You'd expect a former pro with very in-depth game understanding to play at the very tip top level with some 'aim assist' but it doesn't appear to be the case!

Re: DeepMind Challenges for StarCraft

#47

Post by ludamad »

scottjad wrote: post #41

Starcraft is a game that is played with mouse and keyboard (or game controller on console). I think in order to say an AI has beat a human, it should have to use the same interface that a human uses. That's part of the definition of the game. In Go, anyone can place a stone as well as anyone else, it's deciding where to place a stone that's the game. In Starcraft, not everyone can control the interface to the game eq…

But Brood War has been thoroughly explored, and is a much more stable target (SC2 is prone to game-shaking patches). Back when pro play was just ending, I was astonished by the level of play. While players may need a bit to practice against the AI, a good AI spurring more play is really exciting to me.

Re: DeepMind Challenges for StarCraft

#50

Post by fiatmoney »

eru wrote: post #33
dave_sullivan wrote: post #15

> StarCraft is closed source, making it quite challenging to run simulations. One of the techniques used by AlphaGo is reinforcement learning, which involves a huge amount of simulation. In order for DeepMind to overcome this limitation, it’s likely that novel abstractions of the state-space will need to be developed. For their atari work, deepmind was using raw pixel data from the screen. You could do something simi…

And you can run the StarCraft binary in a VM to be able to roll the game state back and forward.

Are there any VMs that give you memory-state level snapshots?
Post reply on HN