AlphaStar: Mastering the Real-Time Strategy Game StarCraft II • Hacker News Board

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#251

Post by gowld » Fri, Jan 25, 2019, 2:41 AM UTC

a_wild_dandan wrote: post #241

gamegoblin wrote: post #67

Earlier quoted context omitted.

In the mass stalker battles, the AI APM exceeded 1000 a few times, and no doubt that most of that was precisely targeted. Whereas a human doing 500 APM micro is obviously going to be far more imprecise. I think a far more interesting limitation would be to cap APM at 150 or so, or to artificially limit action precision with some sort of virtual mouse that reduced accuracy as APM increased.

Here's a graph of AlphaStar's APM versus a professional player's: https://i.imgur.com/TXeLkQK.png Evidently AlphaStar also has a similar Economy of Attention (where the player focuses) to a professional player, at around 30 screens per minute. Additionally, AlphaStar's reaction time is around 350ms, a significant disadvantage over a pro. The skepticism in this thread is absolutely justified but I think it's important…

How can it do 1000 APM if if its reaction time is 350ms? (180/minute)

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#252

Post by gowld » Fri, Jan 25, 2019, 2:43 AM UTC

dx87 wrote: post #181

jgon wrote: post #150

Earlier quoted context omitted.

Even the 200ms reaction time seemed overly slanted towards the AI. I don't think that is the actual reaction time of top pros, in the matches the AI played the human player would teleport in from complete invisibility and try to use an instant cast spell and the AI would have already teleported out. Yes the theoretically may have been constrained to a 200ms reaction time, but in practice the AI was playing at a super…

Another advantage was that the AI is just reading the game state through an API, it doesn't have to look on the screen. The game can be difficult to watch from a pro's perspective since they have to constantly click around the map to see what's happening, but the AI has perfect knowledge of everything it is capable of seeing, all without having to physically move a mouse to click on the screen.

What happens if a human tries to use the API with a custom UI of the human's own choosing? Such a UI might not exist yet, but are there ideas for more efficient UIs that could be built?

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#253

Post by gowld » Fri, Jan 25, 2019, 2:45 AM UTC

candiodari wrote: post #214

thomasfortes wrote: post #195

Earlier quoted context omitted.

But on the other hand, an AI that beats humans using brute force in a game where it makes a ton of difference isn't much fair too.

The funny thing is that once we're talking about the real world, which will come, that incentive actually reverses. At that point the name of the game will be maximizing the advantage the body/infrastructure provides the AI, not minimizing it. Weird.

It's the same principle as a baseball player putting extra weights on the bat in practice.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#254

Post by rhlala » Fri, Jan 25, 2019, 2:45 AM UTC

Trying to solve Imperfect information games is interesting.

But realtime game is not. As computer have edges in boring fileds (apm etc).

I feel the real challenge will be Imperfect information, turn based, and cooperation( teamplay based) for ai.

Unfortunately there are currently no game AFAIK with these characteristics...

Like a 2d turn based counter-strike or dota/lol would be really the good format game to solve.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#255

Post by gamegoblin » Fri, Jan 25, 2019, 2:46 AM UTC

a_wild_dandan wrote: post #241

gamegoblin wrote: post #67

Earlier quoted context omitted.

In the mass stalker battles, the AI APM exceeded 1000 a few times, and no doubt that most of that was precisely targeted. Whereas a human doing 500 APM micro is obviously going to be far more imprecise. I think a far more interesting limitation would be to cap APM at 150 or so, or to artificially limit action precision with some sort of virtual mouse that reduced accuracy as APM increased.

Here's a graph of AlphaStar's APM versus a professional player's: https://i.imgur.com/TXeLkQK.png Evidently AlphaStar also has a similar Economy of Attention (where the player focuses) to a professional player, at around 30 screens per minute. Additionally, AlphaStar's reaction time is around 350ms, a significant disadvantage over a pro. The skepticism in this thread is absolutely justified but I think it's important…

I watched all of the event live and I feel that that graph is deceptive. If a game is 15 minutes and has 3 main battles lasting 15 seconds each, and you use 100 average APM on non-battle time and 1000 APM during battles, your average APM will be 145 but you obviously have a superhuman advantage.

This is compounded by the fact that almost all of AlphaStar’s actions are “useful” whereas a significant amount of the human actions are spammy.

You will typically see a human select a group of units, and fast-click a location in the general direction they want the units to move (to get them started moving that way), and then keep clicking to continuously update the destination to a more precise location. Every click counts as an action. An AI can be perfectly precise and “clicks” the right place the first time.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#256

Post by gamegoblin » Fri, Jan 25, 2019, 2:48 AM UTC

gowld wrote: post #251

a_wild_dandan wrote: post #241

Earlier quoted context omitted.

Here's a graph of AlphaStar's APM versus a professional player's: https://i.imgur.com/TXeLkQK.png Evidently AlphaStar also has a similar Economy of Attention (where the player focuses) to a professional player, at around 30 screens per minute. Additionally, AlphaStar's reaction time is around 350ms, a significant disadvantage over a pro. The skepticism in this thread is absolutely justified but I think it's important…

How can it do 1000 APM if if its reaction time is 350ms? (180/minute)

I believe you are conflating latency and throughput. It might take AlphaStar 350ms to perceive a threat, but once perceived, it might issue many commands at high speed to respond.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#257

Post by ehsankia » Fri, Jan 25, 2019, 2:56 AM UTC

arnaudsm wrote: post #245

Today, 1/1 games without the camera hack were won by the human. This is disappointing, but their PR is a success. Mainstream media is already saying "AI has beaten StarCraft". Another lie for the AI bubble I guess.

It's not "games", as it was a single game, and it came with the big caveat that they didn't have much time to actually prepare and train this one as much. The one that won against Mana was trained for 2 weeks, versus this one that only had one week of training.

While the AI did have an advantage in terms of micro/camera view, it still was able to make decent decision making and independently come up with a bunch of interesting strategies. At the end of the day, that's really the goal of the research, not whether or not it uses the right number of APM or uses the camera properly. Those are just artificial restrictions put to make it look fair and entertaining.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#258

Post by cjbprime » Fri, Jan 25, 2019, 2:58 AM UTC

ascar wrote: post #18

It's amazing what they achieved so far, but I wonder how it would stack up against Serral, who draws a lot of his wins by supremely judging an engagement and continiously gains small advantages over the course of a game. This is a skill even most other professional players only have on a much lower level.

Yes, a best of 9 (?) match against Serral or Maru needs to happen.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#259

Post by arnaudsm » Fri, Jan 25, 2019, 3:07 AM UTC

ehsankia wrote: post #257

arnaudsm wrote: post #245

Today, 1/1 games without the camera hack were won by the human. This is disappointing, but their PR is a success. Mainstream media is already saying "AI has beaten StarCraft". Another lie for the AI bubble I guess.

It's not "games", as it was a single game, and it came with the big caveat that they didn't have much time to actually prepare and train this one as much. The one that won against Mana was trained for 2 weeks, versus this one that only had one week of training. While the AI did have an advantage in terms of micro/camera view, it still was able to make decent decision making and independently come up with a bunch of i…

I would love DeepMind to put that AI on the ladder as they discussed during the last Blizzcon.

The APM and camera restriction is not for entertainment, it's to develop intelligence rather than 1500+ APM. The interesting part of StarCraft II is decision making and the meta of the opponent, and we didn't see that today.

Remember their Dota2 bot that was beaten by a lot of players after a single day. I want to see if AlphaStar can really adapt to the real world, therefore the meta, the real challenge of StarCraft.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#260

Post by sandov » Fri, Jan 25, 2019, 3:09 AM UTC

rhlala wrote: post #254

Trying to solve Imperfect information games is interesting. But realtime game is not. As computer have edges in boring fileds (apm etc). I feel the real challenge will be Imperfect information, turn based, and cooperation( teamplay based) for ai. Unfortunately there are currently no game AFAIK with these characteristics... Like a 2d turn based counter-strike or dota/lol would be really the good format game to solve.

Civilization?