Grandmaster level in StarCraft II using multi-agent reinforcement learning

Post by posterboy » Fri, Nov 01, 2019, 2:07 PM UTC

Strom wrote: post #212

Erlich_Bachman wrote: post #206

Earlier quoted context omitted.

Yes, those might have some impact, but it is clear that the progress is there, with this new APM cap and camera movement etc. You can also see in replays that the AI often makes mechanical mistakes, missing spells, missing units, even ordering wrong units from outside the screen - so it surely seems that if it's win rate was conditioned in any strong way on its sheer mechanical ability, it would have learned to not m…

The mistakes it makes are due to bad decisions. There have been no claims by DeepMind that they have some sort of chaos engineering [1] going on where the AI decides one thing and then the output system actually does another thing. Also I think you overestimate the AI/IT knowledge of these top players that they're consulting. I have great respect towards them, but they're not renaissance men [2] who both play 10 hour…

Post by MiracleUser » Fri, Nov 01, 2019, 3:34 PM UTC

floitsch wrote: post #225

MiracleUser wrote: post #80

Earlier quoted context omitted.

> a well executed strategy with few errors often wins, even if it wasn't optimal I think this is hits the chord with why a lot of people are talking about this bot as cheating more than they are being outplayed. It's like fighting an aimbot in an FPS. They arent outsmarting you, but the mechanical consistency is inhuman and you are unable to force mistakes. At best itll feel like playing someone on their best day. Th…

I don't think the comparison with aimbots is fair. Aimbots are more like a perfect micro. In the beginning (when they did their first show match), Alphastar was insane at that. Now the micro is not giving an advantage anymore. Where alphastar shines, is in making a strategy work. It won't attack into something that looks dangerous. It won't forget to build more units. It won't be distracted on two fronts. (That said:…

Post by the_af » Fri, Nov 01, 2019, 10:15 PM UTC

skybrian wrote: post #284

the_af wrote: post #241

Earlier quoted context omitted.

I think part of the problem is that every videogame is a parlor trick in a sense. Unless you are a tournament player or someone who enjoys a really hard challenge, the bulk of the customers who buy the game just want to enjoy the illusion of a challenge. You don't really need a complex AI directing the hordes of enemies you want to defeat; you just want the illusion of battling enemies and emerging the victor, and ho…

While there are certainly plenty of parlor tricks and other illusions, I think in the best case, a game can contain a finely tuned learning experience, where by training you actually do get better at something. (Often something unimportant, but still fun.) Throwing people into the deep end of the pool usually doesn't work so well. Scaling down the difficulty helps, but really what you want is challenges that teach yo…

Post by yters » Sat, Nov 02, 2019, 2:54 AM UTC

falcor84 wrote: post #309

yters wrote: post #105

What would be interesting is to limit the AI processing speed to human capacity, which is something like 60 bits per second. In all these AI v. Human games I see, it is really apples to oranges because the human consumes vastly less resources and compute cycles to perform at the same level as the AI. And when I say 'vast' I mean Vast. There is like a quintillion factor difference between the AI and the human. There i…

> What would be interesting is to limit the AI processing speed to human capacity, which is something like 60 bits per second. What part of human processing capacity is this slow?

Post by yters » Mon, Nov 04, 2019, 2:40 PM UTC

whichquestion wrote: post #199

yters wrote: post #105

What would be interesting is to limit the AI processing speed to human capacity, which is something like 60 bits per second. In all these AI v. Human games I see, it is really apples to oranges because the human consumes vastly less resources and compute cycles to perform at the same level as the AI. And when I say 'vast' I mean Vast. There is like a quintillion factor difference between the AI and the human. There i…

It would be interesting to see if there are any meta reports on people doing research on the topic of resource constrained AI. Has anyone explored whether or not an AI can improve on its own algorithm while being heavily resource constrained? Is the ability to use less resources a limit of our current hardware? Do we see the current hardware performance improvement trajectory being able to reduce the amount of resour…