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

11–20 of 137 posts

Re: DeepMind Challenges for StarCraft

#11

Post by tonyle »

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 like this idea. To be fair, You need five computers to communicate with each other. It will be a huge mark for ai if they can actually learn to communicate with effectively for achieving the goals. Vary the performance of each ai and allow them to swear at each other could get very interesting. I wonder if ai can emulate the toxic side of gamers......

Re: DeepMind Challenges for StarCraft

#12

Post by smilekzs »

dogma1138 wrote: post #7
detaro wrote: post #4

Earlier quoted context omitted.

If anyone, Google has the image recognition and robotics tech to make a robot sitting in front of a screen, with keyboard and mouse ;) Yes, anything where the interface to the game becomes critical is difficult to fairly compare with humans. Board games can use a human as an actuator, micro-heavy games hopefully won't for a long time...

Not really since electromechanical engineering would then be the bottle neck. If you want "fairness" you can limit the instructions to what keyboard and mouse can actually interpret as in the limited latency between instruction that both the game, the OS, and the hardware can support.

The game is capable of accepting a much higher APM than Korean pro players are capable of pulling off even at peak. IMHO the AI should be subject to an APM limit (e.g. sliding window).

Re: DeepMind Challenges for StarCraft

#13

Post by econnors »

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).

Re: DeepMind Challenges for StarCraft

#14

Post by Mithaldu »

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

Re: DeepMind Challenges for StarCraft

#15

Post by dave_sullivan »

> 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 similar for starcraft. I suspect the actual machine learning question is 'given a sequence of n frames of the game, where should i click next? repeat.'

A training set might look something like video of a game with a text file recording X,Y positions for every click and a timestamp that can be synced to the video. They need lots and lots of those.

From there things get drastically more complicated. To go from very unstructured data like that and form higher level representations that can be used for long term planning and strategy... That would be quite a feat.

Re: DeepMind Challenges for StarCraft

#16

Post by danharaj »

ktRolster wrote: post #9
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 think it's pretty simple, you just take the starcraft AI, reduce the number of units it can handle at a time, maybe simplify its economy logic, and then let it go. Easy.

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.

Re: DeepMind Challenges for StarCraft

#17

Post by MawNicker »

dogma1138 wrote: post #7
detaro wrote: post #4

Earlier quoted context omitted.

If anyone, Google has the image recognition and robotics tech to make a robot sitting in front of a screen, with keyboard and mouse ;) Yes, anything where the interface to the game becomes critical is difficult to fairly compare with humans. Board games can use a human as an actuator, micro-heavy games hopefully won't for a long time...

Not really since electromechanical engineering would then be the bottle neck. If you want "fairness" you can limit the instructions to what keyboard and mouse can actually interpret as in the limited latency between instruction that both the game, the OS, and the hardware can support.

I don't think that's quite fair. Human's aren't anywhere near what the system can handle. The most "fair" thing I can think of would be to add latency to every mouse movement using Fitts's law.

https://en.m.wikipedia.org/wiki/Fitts%27s_law

It may also be interesting to model the state of the keyboard hand. Instead of allowing the computer to access keyboard shortcuts directly it could be forced to operate a virtual hand that is in turn operating a virtual keyboard. Constraints could be added to the speed of various finger movements. This provides balance but also captures authentic strategic tradeoffs. Like the resting position of the hand. I imagine if you had a nice visualization it could even reveal subtle optimizations that were practical for humans.

Re: DeepMind Challenges for StarCraft

#18

Post by detaro »

tonyle wrote: post #11
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 like this idea. To be fair, You need five computers to communicate with each other. It will be a huge mark for ai if they can actually learn to communicate with effectively for achieving the goals. Vary the performance of each ai and allow them to swear at each other could get very interesting. I wonder if ai can emulate the toxic side of gamers......

Would be interesting on what level the communication can be done. Do you give them a predefined, limited, game-specific vocabulary and make do with that? Or can you have the networks "talk" in some random set of symbols, with a meaning they have established while learning?

Re: DeepMind Challenges for StarCraft

#19

Post by TulliusCicero »

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

If that was true, then bots would already easily dominate humans, just like they can for fighting games.

But they don't; even moderately competitive players can beat the best bots.

Post reply on HN