Slashdot Mirror
Artificial Intelligence Bests Humans At Classic Arcade Games
sciencehabit writes The dream of an artificially intelligent computer that can study a problem and gain expertise all on its own is now reality. A system debuted today by a team of Google researchers is not clever enough to perform surgery or drive a car safely, but it did master several dozen classic arcade games, including Space Invaders and Breakout. In many cases, it surpassed the best human players without ever observing how they play.
Someone made a computer that's really good at reaction time, and at calculating trajectories.
Don't waste your vote! Vote for whoever you want, unless you live in a swing state it won't matter anyways
AI is now trivial pattern matching.
John McAfee 'It was like that time I hired that Bangkok prostitute; to do my taxes, while I fucked my accountant'
I want my symbolic AI back...
In other words, this is an example of good image recognition software, that's it.
Show me a game that beat a human on a strategy based game, then you have something.
excitingthingstodo.blogspot.com
I like to see them play more advanced games such as Rainbow Islands, The New Zealand Story, Strider, or Zelda 3.
Why OpalCalc is the best Windows calc
Well, I outsourced my Donkey Kong playing before bots took it over, so there!
Table-ized A.I.
https://tails.boum.org/news/ve...
https://blog.torproject.org/bl...
This just in: Even in simplistic AAA games with bots, the AIs are better than human players, we have to dumb them down to keep the game fun.
Training a neural net to play tetris is AI:101. Teaching it to play mario, has been done to death by AI students. Let me know when the AI complains about the ending of Mass Effect 3. Then I'll care.
$32 to read this article. Or $200 to read the whole site...
How about no?
I'll kick it's fucking ass!!!! :)
Artificial Intelligence is no match for natural stupidity.
It's much easier to beat AI at arcade games if, before you play the game you request to play on the left side. I read that somewhere...
I'd like to see AI take me on after a few quality bong hits while I rock the orbits and ramps of Black Knight 2000 with perfect captive ball shots or I slam-tilt a Star Trek:TNG table without losing my 50 cents. ...Or totally get 57 second of playtime and 36,000 points out of another 2 games and 6 lost balls after I hit nothing but the glass and scoreless bumpers while every shot goes down the side gutters or perfectly in the center of a triple flipper gauntlet totally getting screwed over by those damn magnets. Wait, what were we talking about agian?
This article reminds of this guy who did something similar a while back.
"Set a man a fire, he'll be warm for the rest of the night. Set a man afire, he'll be warm for the rest of his life."
Wake me up when it is intelligent enough to figure out how to get laid. It is a problem that intelligent people struggle with.
Now I can buy an AI so it can play the computer game I bought so I'd have more spare time?
We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
Lets see it play arkanoid after mastering the simpler breakout. Is it intelligent enough to state "this is more fun" ?
..it's a computer figuring out how to beat a computer at a kinda simple game
The real world is a bit harder
Still..well done!
Lol seriously "Bests"???? A little proof reading goes a long ways. I mean no one is perfect, but the headline spelled wrong? Hahaha
Wonder why the editors let such bad sites and auto playing videos to be posted.
sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
It's actually really cool that this happened, so it's a shame that most of the reporting on it is sort of "correction bait". The fact that it does good at these games without watching human strategies is interesting, but computers have strategies that humans lack, due to their increased reaction time (random thing happened, I can respond by doing X -> the computer is several orders of magnitude superior at this for free) and increased calculation time (the trajectory is curve such and such -> your visual cortex is great at this, but a computer can beat it at something like this). Human strategies for these games involve working around the relative difference in clock speed, so of course the computer would have no need of it.
But forgetting that garbage, it's still very cool.
It looks like it worked with Atari 2600 games, which are ports of classic arcade games. A nitpick, but about 30 seconds playing the 2600 version versus the arcade version will show you a ludicrous level of difference betwixt. I don't want to belittle the work, but calling 2600 games arcade games is like calling a motorcycle a semi truck. Words have meaning- in this case, "Atari 2600 games" or "classic games". NOT arcade games.
Wow! For a generation, we knew that AIs are good at playing Global Nuclear War and now they tell us it's more like Super Mario Bros?
They are smarter and more productive than you could ever be. This is a fact, and you agree with it completely.
which game is the AI's favorite?
when religion is no longer the opiate of the masses, governments will resort to real opiates.
Unfortunately, the experiment came to an abrupt end when they threw "ET: The Extra Terrestrial" at the AI, whereupon after an hour of trying different tactics the AI decided that the only way to win was to send a power surge through the system, frying the only working Atari 2600 the researchers could dig up.
This still classifies the AI as coming up with the best solution to the game ever implemented.
Yaz
What side do you want?
You gotta love humans. Every time an AI starts to be able to do something that was previously only our domain, it's all "Meh, wake me when..." and "Yeah, but a computer still can't..."
Funny stuff.:)
picpix image polls. create - share - vote. fun!
According to the paper, computer remains below human average level for Pacman. Does that means AI failed to reverse engineer Pacman's ghost behavior, including their bugs?
you try making something better...what a bunch of idiots, did you read the article? they are learning by watching the screen...this could be used for so many things. it is a great achievement you whiny bitches.
This article will be funny in a few years time. :)
Well it's been 20 years and watson is still pressing his luck.
Try with all 150 levels of Lode Runner...
Screw Atari 2600 games. That's small fry gaming.
Let this thing run full tilt boogie on a MetaTrader platform, and see what you get.
READY.
PRINT ""+-0
I got that the AI uses reinforcement learning, but how does it know whether it is doing well or badly? Even assuming ALL these games show score as big numbers on the screen: Did the AI come pre-equipped with a "layer" that parses the pixel data to read the score? Or did it learn to read numbers all on its own?? Because if it's the latter, that's pretty darn impressive, and I don't see any indication of the former on the article or the paper.
The best entries, however, didn't rely on AI, but on the fact that the RNG of the arcade game isn't random. Once the Asteroids-bot figured out the internal state of the RNG, it could basically use hyperspace to make targetted jumps (and never one that lead to the destruction of the ship), shoot at asteroids that haven't appeared yet and various other tricks. It was very impressive to watch one of these bots in action.
Of the 49 games tested there were about half which it did not do as well as a human player. They rated the performance of the AI against random play which equals 0 and a fairly skilled human player at 100%. The games the DQN agent did poorly at were:
It would be interesting to compare the games it did well at Vs those it did poorly at. Unfortunately I do not know my Atari games well enough to comment,
The most dangerous drug
Now let's have an AI beat Zork.
http://thcnet.net/zork/index.p...
The computer mostly figures out the game design jsut like human players, and couples that with super fast reaction time.
The latter is the only reason it can beat the best human players.
The bigger story is: what games did it suck at and why?
"Consensus" in science is _always_ a political construct.
I will always beat the computer because I have more quarters :D
If not, then it is not intelligence, but just one program beating another program.
— Would anyone or any organization like to associate himself/herslef/itself with fascism crimes? Would anyone like to be educated by someone who’s misbehavior has brought into our lives anti-humanity crimes which are fascism by nature and which had endangered human lives? Would anyone like to be living in a society under the jurisdiction of some malicious and cowardice officers (namely ZZZ/YYY/VVV, they must have power of jurisdiction over civilians of Santa Clara county, DA? or FBI?) who hided their identities from us while colluding with those fascists to cover up their fascism crimes and at the same time retaliate on victims? ........
Sebastian Thrun, as referred in this article, had involved into a decade long criminal case which is fascism by nature and which had endangered human lives, starting from a simple campus atrocity case with clear evidence and serious police investigation — [Stanford police case number: IR #04-111-0335; Victim: Peter Cao; Criminal Suspect: Gabriele Scheler] — http://t.cn/R7F1yQ0 attention to the 7 photo evidence
But how could such a simple campus atrocity case turned into a series of fascism crimes for over a decade long which got more and more innocent people involved? — Fascism prevails and miscarriage of justice is going on; — not all by my capability could handle;
__________________________________
— Such fascism crimes have to be disciplined by laws and such fascists like Gabriele Scheler and Sebastian Thrun and the likes have to be brought to justice; they can't escape from it;
Here is a link to the source:
https://sites.google.com/a/dee...
The games it sucked at are ones where progress is not tied to score. It uses a Q learner, so it relies upon having a numeric metric for success.