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

31–40 of 137 posts

Re: DeepMind Challenges for StarCraft

#31

Post by im3w1l »

hmate9 wrote: post #6

I think poker would also be a great challenge. It is a special game because as well as the math, you also have to understand your opponent and adjust accordingly. It'd be interesting to see weather DeepMind can beat professional poker players who have different playing styles.

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 would be known as a Mixed Strategy.

Or am I missing something?

Re: DeepMind Challenges for StarCraft

#32

Post by drwl »

ktRolster wrote: post #21
Mithaldu wrote: post #14

Earlier quoted context omitted.

The problem is, as ActionButton argues in this review of Diablo 2 [0], Starcraft is a game that may contain some amount of strategy, but wherein the element of strategy is strongly over-powered by a reflex-based combat system more akin to Street Fighter than anything else. [0] http://www.actionbutton.net/?p=518

wherein the element of strategy is strongly over-powered by a reflex-based combat system This isn't true, in general a bigger army will beat a smaller army every time. After you can make equal size armies, the next problem is army positioning and when to take engagements. Finally, after you can do all that, then you can get an extra bonus to your power by microing really well. But not every micro is about speed - mos…

It's not always the case where smaller armies lose to big armies. There are many situations in Starcraft where superior micro of less units can taken on more units. One example is Phoenixes versus mutalisks. For those who don't play, Phoenixes are faster and have slightly longer range than mutalisks. Phoenixes can infinitely shoot and run and kill of mutalisks.

Re: DeepMind Challenges for StarCraft

#33

Post by eru »

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.

Re: DeepMind Challenges for StarCraft

#35

Post by Monory »

Well, anyone who says that advantage in micromanagement is not a big thing should see "Automaton 2000" videos. Given that automaton is a map script and thus can have virtually unlimited APM, it beats people from a horribly disadvantageous positions (40 banelings vs 21 marine [1], or 100 zerglings vs 20 sieged tanks [2]).

[1]: https://www.youtube.com/watch?v=DXUOWXidcY0 [2]: https://www.youtube.com/watch?v=IKVFZ28ybQs

Re: DeepMind Challenges for StarCraft

#36

Post by danharaj »

ktRolster wrote: post #23
danharaj wrote: post #16

Earlier quoted context omitted.

The interactions between individual unit types in a game like DOTA are much more complicated than, say, the interactions between marines, zerglings, and zealots; there are many more unit types, too.

as someone else pointed out, the interactions between the units are like fighting games. Computers already have the advantage at fighting games (like Streetfighter). Micro and unit control is where the AI has the advantage.

The complexity of the unit interactions also has a strategic layer (drafting, lane assignment, timing) which may be far more difficult to train and isn't just purely the micro aspect of the problem.

Re: DeepMind Challenges for StarCraft

#37

Post by dwaltrip »

Mithaldu wrote: post #14
DanBlake wrote: post #3

One of the issues to overcome is the advantage machines can have in individual unit manipulations vs what a human can do in terms of APM https://www.youtube.com/watch?v=SZawUuAccnc

The problem is, as ActionButton argues in this review of Diablo 2 [0], Starcraft is a game that may contain some amount of strategy, but wherein the element of strategy is strongly over-powered by a reflex-based combat system more akin to Street Fighter than anything else. [0] http://www.actionbutton.net/?p=518

The strategic complexity of StarCraft is easily several orders of magnitude above Street Fighter.

Re: DeepMind Challenges for StarCraft

#38

Post by eru »

im3w1l wrote: post #31
hmate9 wrote: post #6

I think poker would also be a great challenge. It is a special game because as well as the math, you also have to understand your opponent and adjust accordingly. It'd be interesting to see weather DeepMind can beat professional poker players who have different playing styles.

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.

Re: DeepMind Challenges for StarCraft

#39

Post by StavrosK »

dwaltrip wrote: post #37
Mithaldu wrote: post #14

Earlier quoted context omitted.

The problem is, as ActionButton argues in this review of Diablo 2 [0], Starcraft is a game that may contain some amount of strategy, but wherein the element of strategy is strongly over-powered by a reflex-based combat system more akin to Street Fighter than anything else. [0] http://www.actionbutton.net/?p=518

The strategic complexity of StarCraft is easily several orders of magnitude above Street Fighter.

The GP didn't disagree. He said that the strategic component is overpowered by the need for reflexes.

Re: DeepMind Challenges for StarCraft

#40

Post by diskcat »

Monory wrote: post #35

Well, anyone who says that advantage in micromanagement is not a big thing should see "Automaton 2000" videos. Given that automaton is a map script and thus can have virtually unlimited APM, it beats people from a horribly disadvantageous positions (40 banelings vs 21 marine [1], or 100 zerglings vs 20 sieged tanks [2]). [1]: https://www.youtube.com/watch?v=DXUOWXidcY0 [2]: https://www.youtube.com/watch?v=IKVFZ28ybQs

Yeah. infinite apm would make stuff like marine being able to turn around and shoot instantly OP. it was just impossible to exploit before with human reflex.

also the APM is not unlimited, it is only very high.

Post reply on HN