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

71–80 of 137 posts

Re: DeepMind Challenges for StarCraft

#71

Post by derefr »

nickpsecurity wrote: post #54
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

I agree. It's one of only areas the AI's have been hood at. Pathfinding and build orders being other two. AI should be limited to a specific number of actions a minute comparable with opposing player or best human champ. Then, we're grading it on its "thinking" instead of dexterity. They better keep fog of war on too.

Or, the AI could be set up like AlphaGo was: as a computer giving instructions to a merely human player. I'd love to see what a powerful StarCraft AI would do if trained to "predict and compensate for" not only its opponent, but also the inevitable human errors in faithfully executing its strategy. A certain Sector Command and Control Unit springs to mind...

Re: DeepMind Challenges for StarCraft

#72

Post by wlievens »

derefr wrote: post #69
barbs wrote: post #52

Earlier quoted context omitted.

From the 2015 AIIDE Starcraft AI competition report[0]. > ""Why not StarCraft 2?" > This is the question we always get asked when we tell people we are doing a BroodWar AI competition. This competition relies completely on BWAPI as a programming interface to BroodWar. BWAPI was created by reverse engineering BroodWar and relies on reading and writing to the program memory space of BroodWar in order to read data and i…

It has always seemed to me that there is a truly "proper" way to construct an AI 'bot' for a networked game, and that is to write your own headless game client software that connects to the game's network—emulating the physics well enough to avoid desynchronization with one's opponent, but otherwise being entirely its own program, rather than having anything to do with the reference client per se .

That would be an order of magnitude more work though, right?

Re: DeepMind Challenges for StarCraft

#73

Post by eru »

fiatmoney wrote: post #50
eru wrote: post #33

Earlier quoted context omitted.

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?

Xen does. Basically all of them have to, if you want to freeze your VM, or move it to a different server whilst it's running.

Re: DeepMind Challenges for StarCraft

#74

Post by TulliusCicero »

drwl wrote: post #32
ktRolster wrote: post #21

Earlier quoted context omitted.

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.

I'm not sure this is true, even with infinite APM micro, and I have a whole of experience microing phoenixes against mutas. Well, maybe after the range upgrade it is.

Re: DeepMind Challenges for StarCraft

#75

Post by MacsHeadroom »

beambot wrote: post #57
barbs wrote: post #52

Earlier quoted context omitted.

From the 2015 AIIDE Starcraft AI competition report[0]. > ""Why not StarCraft 2?" > This is the question we always get asked when we tell people we are doing a BroodWar AI competition. This competition relies completely on BWAPI as a programming interface to BroodWar. BWAPI was created by reverse engineering BroodWar and relies on reading and writing to the program memory space of BroodWar in order to read data and i…

So why not use Matt's version for SC2 that doesn't provide map hacks? https://graphics.stanford.edu/~mdfisher/GameAIs.html

Maybe they didn't know about it? First I've heard of it.

Looks really great. I hope they look into this.

Re: DeepMind Challenges for StarCraft

#76

Post by dragontamer »

derefr wrote: post #71
nickpsecurity wrote: post #54

Earlier quoted context omitted.

I agree. It's one of only areas the AI's have been hood at. Pathfinding and build orders being other two. AI should be limited to a specific number of actions a minute comparable with opposing player or best human champ. Then, we're grading it on its "thinking" instead of dexterity. They better keep fog of war on too.

Or, the AI could be set up like AlphaGo was: as a computer giving instructions to a merely human player. I'd love to see what a powerful StarCraft AI would do if trained to "predict and compensate for" not only its opponent, but also the inevitable human errors in faithfully executing its strategy. A certain Sector Command and Control Unit springs to mind...

A huge amount of Starcraft is the intense APM training regiment that the pros undergo.

APM is a huge indicator of Starcraft "skill". Its not the only thing of course, but winning "micro-battles" greatly changes the game.

I don't care how good Michael Jordan is. He'll never "win" a game of basketball vs a standard professional by shouting commands to an average joe.

Similarly, no average joe will be able to perform a muta-harass while retaining full-speed, taking only a single missile from a Turret. That sort of "micro-skill" takes practice and dexterity.

Re: DeepMind Challenges for StarCraft

#77

Post by spacehome »

ShardPhoenix wrote: post #67
ktRolster wrote: post #20

Artosis wrote his view on the topic, it's probably worth a read: http://espn.go.com/esports/story/_/id/15019778/infinite-apm-...

It sounds like he has no idea about the machine learning basis of Alpha Go (and therefore presumably any future Starcraft AI) and thinks all this complex decision making has to be programmed in by hand (which would indeed be nigh-impossible).

Yea, Artosis seems pretty ignorant of AI and mixed strategies in game theory.

Re: DeepMind Challenges for StarCraft

#78

Post by derefr »

dragontamer wrote: post #76
derefr wrote: post #71

Earlier quoted context omitted.

Or, the AI could be set up like AlphaGo was: as a computer giving instructions to a merely human player. I'd love to see what a powerful StarCraft AI would do if trained to "predict and compensate for" not only its opponent, but also the inevitable human errors in faithfully executing its strategy. A certain Sector Command and Control Unit springs to mind...

A huge amount of Starcraft is the intense APM training regiment that the pros undergo. APM is a huge indicator of Starcraft "skill". Its not the only thing of course, but winning "micro-battles" greatly changes the game. I don't care how good Michael Jordan is. He'll never "win" a game of basketball vs a standard professional by shouting commands to an average joe. Similarly, no average joe will be able to perform a…

You don't think it'd be interesting to take a player who's already one of the top players, and measure the marginal gains of them doing their own macro+micro, vs. just doing micro and leaving macro to the AI?

Re: DeepMind Challenges for StarCraft

#79

Post by bottled_poe »

lumpypua wrote: post #66
komaromy wrote: post #62

Earlier quoted context omitted.

> If you can control 1 unit it's trivial to control 100. Control them, sure-kiting 100 units at a time would be a breeze-but using them together in a coherent way is drastically more difficult.

From an above poster: https://www.youtube.com/watch?v=IKVFZ28ybQs

The developer of the AI in this video even states that this AI is applies 300 APM per unit. That's 30000 actions per minute. There are simply not enough decisions to make in League of legends to make use of that power.

Re: DeepMind Challenges for StarCraft

#80

Post by ktRolster »

derefr wrote: post #78
dragontamer wrote: post #76

Earlier quoted context omitted.

A huge amount of Starcraft is the intense APM training regiment that the pros undergo. APM is a huge indicator of Starcraft "skill". Its not the only thing of course, but winning "micro-battles" greatly changes the game. I don't care how good Michael Jordan is. He'll never "win" a game of basketball vs a standard professional by shouting commands to an average joe. Similarly, no average joe will be able to perform a…

You don't think it'd be interesting to take a player who's already one of the top players, and measure the marginal gains of them doing their own macro+micro, vs. just doing micro and leaving macro to the AI?

We can see that now, with the new Archon mode, which allows two players to control the units together.
Post reply on HN