Slashdot Mirror
OpenAI Built Gaming Bots That Can Work As a Team With Inhuman Precision (qz.com)
OpenAI said on Monday that its newest AI bots can hold their own as a team of five against human gamers at Dota 2, a multiplayer game popular in e-sports for its complexity and necessity for teamwork. The AI research lab is looking to take the bots to Dota 2 championship matches in August to compete against the pros. From a report: Dota 2 is a challenging game for AI to master simply because of the amount of decisions that the players have to juggle. While chess can end in fewer than 40 moves, and Go fewer than 150, OpenAI's Dota 2 bots make 20,000 moves over the course of a 45 minute game. While OpenAI showed last year that the bots could go one on one against a human professional in a curated snippet of the game, the company wasn't entirely sure that they could scale up to five against five.
But the research team doesn't credit this breakthrough to a new technique or a lightbulb moment, rather a simple idea. "As long as the AI can explore, it will learn, given enough time," Greg Brockman, OpenAI's chief technology officer, told Quartz. The bots learn from self-play, meaning two bots playing each other and learning from each side's successes and failures. By using a huge stack of 256 graphics processing units (GPUs) with 128,000 processing cores, the researchers were able to speed up the AI's gameplay so that they learned from the equivalent of 180 years of gameplay for every day it trained.
But the research team doesn't credit this breakthrough to a new technique or a lightbulb moment, rather a simple idea. "As long as the AI can explore, it will learn, given enough time," Greg Brockman, OpenAI's chief technology officer, told Quartz. The bots learn from self-play, meaning two bots playing each other and learning from each side's successes and failures. By using a huge stack of 256 graphics processing units (GPUs) with 128,000 processing cores, the researchers were able to speed up the AI's gameplay so that they learned from the equivalent of 180 years of gameplay for every day it trained.
An intelligence is self emerging, it knows what to do without training. Having to train something means it is not intelligence, so by extension not an artificial intelligence.
If the only thing that matters is APM, there's no point in playing.
amirite
"Damn it!"
"what?"
"I just found out we're bots in a giant stack of GPUs"
"uhhh?"
"I mean, dumbass, our entire existence means nothing more than training up some stupid AI to beat us!"
"no way!"
I remember playing against Quake CTF bots that worked as a team. There were team deathmatch bots that would learn maps & communicate.
Why does this conjure up images of hordes of inhumanely fast robots swarming cities and taking out citizens and soldiers with ease... How long until there forms an upperclass completely immune to revolution or the conscience of its human military?
You mean that kind of inhuman?
...it can be applied to important things like X and Y and Z! We promise. It isn't just for games. This is real important stuff.
A massive amount of GPUs and CPUs thrown at the problem.
this amazing news needs a new word! lets call it, botting!
When humans start looking to bots to figure out the meta game that'll take out half the fun
It would be interesting to see how the AI performs when restricted to the same equivalent wattage as the human brain consumes in calories of glucose. Let's be generous and only look at compute... not counting power for HVAC.
And the AI's will never forget even the smallest detail and always use its knowledge to 100% efficiency.
If it was confined to games it would already be scary enough. Now imagine the same thing being applied to AI connected to real-life machines.
#DeleteFacebook
Banging on a keyboard and hanging onto a joy-stick is not sport no matter how much you sweat while guzzling down sugar water with caffeine and what not.
Actually, playing vid games past your teen years is pathetic to begin with.
Hi people! One of my friends wanted to know if her boyfriend was cheating on her and I recommended; spymasterpro3x@ g mail . com to her based on my wonderful experience with them. She contacted them shortly for Facebook hack and phone hack at a cheap cost. Within few hours, She was able to successfully hack his account and secure the information she needed. Both of us are extremely grateful for his assistance in securing our passwords. You can also contact them for all hacking services you require
See Hans Moravec's informed speculations like his book "Mind Children": https://www.goodreads.com/book...
Or going beyond that to the nature of consciousness and reality:
http://www.frc.ri.cmu.edu/~hpm...
And see also Vernor Vinge's various writings on a "Singularity".
That said, hedging our bets by making the world a happier and healthier and more resilient place for everyone right now before a singularity is probably not a bad idea given our trajectory out of any singularity may have a lot to do with out path into one.
A 21st century issue: the irony of technologies of abundance in the hands of those still thinking in terms of scarcity.
You spent the entire day reading creimer's old blogs (a quarter-million words)? You are seriously a sad fuck.
Weren't you going to retire off your trolls?
Shit talk them and annoy them to drive traffic to your content?
I would think this pleases you everything is going according to plan,
Comment removed based on user account deletion
Dota 2? Complex? Starcraft laughs at this, it must be so hard to micro one unit against a few enemies.
It would be interesting to know if there's one "processor" coordinating the 5 bots, or 5 independent processors that need to communicate with each other about what decisions to take, as human do traditionally by using voice-chat.