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

111–120 of 137 posts

Re: DeepMind Challenges for StarCraft

#111

Post by LetaBot »

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

Using that on Battle.net violates the TOS. So your account will get banned if you do that.

Re: DeepMind Challenges for StarCraft

#112

Post by nkrisc »

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…

By forcing a bot to use a keyboard and mouse, it's no longer so much an AI challenge but an engineering challenge of creating robotic limbs that match human performance, totally unrelated. The two aspects should be separated. Arguably, the AI aspect is far more interesting as it relates to StarCraft.

Re: DeepMind Challenges for StarCraft

#113

Post by LetaBot »

sesutton wrote: post #106
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

I'm a little worried that the AI will quickly develop a simple early game strategy where it sacrifices economy for early units (an "all-in") that never loses because of its perfect unit control. The AIs unit control speed may have to be limited to get interesting results where it has to use strategy.

If the human player builds a wall, he/she will be ahead against a rushing bot.

Re: DeepMind Challenges for StarCraft

#114

Post by obl »

nkrisc wrote: post #112
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…

By forcing a bot to use a keyboard and mouse, it's no longer so much an AI challenge but an engineering challenge of creating robotic limbs that match human performance, totally unrelated. The two aspects should be separated. Arguably, the AI aspect is far more interesting as it relates to StarCraft.

I think the point was mostly to only let the bot have as much information as a player would get on the screen : no omniscient knowledge about the state of every visible unit on the map. You'd probably also want to rate limit the inputs, including changing the viewport position, to something reasonable.

Re: DeepMind Challenges for StarCraft

#115

Post by mizzao »

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

Agreed. It also wouldn't be very interesting to watch a human-AI game where the human is better at planning and tactics but the AI just wins even uphill battles due to insane micro.

Re: DeepMind Challenges for StarCraft

#116

Post by Umn44 »

TulliusCicero wrote: post #19
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

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.

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

That's because the programmers are bad at AI for that kind of game. It just means human beings don't understand how to make a good AI for a game like starcraft. AKA the human being being the idiot that doesn't understand how to make one.

Re: DeepMind Challenges for StarCraft

#117

Post by ygra »

obl wrote: post #114
nkrisc wrote: post #112

Earlier quoted context omitted.

By forcing a bot to use a keyboard and mouse, it's no longer so much an AI challenge but an engineering challenge of creating robotic limbs that match human performance, totally unrelated. The two aspects should be separated. Arguably, the AI aspect is far more interesting as it relates to StarCraft.

I think the point was mostly to only let the bot have as much information as a player would get on the screen : no omniscient knowledge about the state of every visible unit on the map. You'd probably also want to rate limit the inputs, including changing the viewport position, to something reasonable.

You'd probably end up with a bot that simply rapidly moves the viewport over the whole map over and over again to give commands and see what is there. That's inconveniencing an AI slightly because now things are "seen" with a few frames latency instead of immediately, but I doubt it'd make a difference.

Re: DeepMind Challenges for StarCraft

#118

Post by HCIdivision17 »

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

Watching the zerglings somehow wash through that tank barage was just ... demoralizing. Those little buggers are not supposed to be a hard counter to tanks, dammit! Fighting against Automaton 2000 is like having your own personal Kaizo assaulting your base.

I think this really demonstrates why putting in APM limits is super important, and as brought out elsewhere also making the computer input via mouse/keyboard and get data from the screen (maybe just a filter to ease up on the CV bits?). A lot of the fun in watching a StarCraft map is seeing how the big picture is balanced against the details, and where a person's limited congnition flows from one focus to another. Limited knowledge and scope of sight play a huge part in the skill.

But mostly I'm just ranting because dodging the splash damage feels unfair; goes against everything I stand for. Next we'll start seeing 5 Skill Rays bulldoze the map! (I'm going to be looking into this a lot more after work - it seems like a super cool project!)

Re: DeepMind Challenges for StarCraft

#119

Post by HCIdivision17 »

dsl wrote: post #58
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…

Game replays (including all the fun data like player clicks, unit selection, movements, and exact timing) are stored in an easily parsable format. https://github.com/GraylinKim/sc2reader/wiki/Replay-Format-H...

This has the immense advantage that there's a large corpus of games available to learn from as well. I don't think Battle.Net saves all games ever (only locally on the computer), there's still many thousands available online.

But man, if Battle.Net did save all of them, there'd likely be hundreds of thousands, if not millions, available. That'd be pretty spectacular as a training set!

Re: DeepMind Challenges for StarCraft

#120

Post by coryfklein »

mizzao wrote: post #115
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

Agreed. It also wouldn't be very interesting to watch a human-AI game where the human is better at planning and tactics but the AI just wins even uphill battles due to insane micro.

I would LOVE to see an AI vs AI game though where the AI had no restrictions on APM/micro.

I mean, what would an AI come up with given just mass zerglings vs mass zerglings. Would love to see the strategies possible with near unlimited attention and APM.

Post reply on HN