Slashdot Mirror
Microsoft's AI Is the First to Reach a Perfect Ms. Pac-Man Score (theverge.com)
Maluuba, a deep-learning team acquired by Microsoft in January, has created an AI system that has achieved the perfect score for Ms. Pac-Man. According to The Verge, the AI system "learned how to reach the game's maximum point value of 999,900 on Atari 2600, using a unique combination of reinforcement learning with a divide-and-conquer method." From the report: Though AI has conquered a wealth of retro games, Ms. Pac-Man has remained elusive for years, due to the game's intentional lack of predictability. Turns out it's a toughie for humans as well. Many have tried to reach Ms. Pac-Man's top score, only coming as close as 266,330 on the Atari 2600 version. The game's elusive 999,900 number though, has so far only been achieved by mortals via cheats. Maluuba was able to use AI to beat the game by tasking out responsibilities, breaking it up into bite-sized jobs assigned to over 150 agents. The team then taught the AI using what they call Hybrid Reward Architecture -- a combination of reinforcement learning with a divide-and-conquer method. Individual agents were assigned piecemeal tasks -- like finding a specific pellet -- which worked in tandem with other agents to achieve greater goals. Maluuba then designated a top agent (Microsoft likens this to a senior manager at a company) that took suggestions from all the agents in order to inform decisions on where to move Ms. Pac-Man. The best results came when individual agents "acted very egotistically" and the top agent focused on what was best for the overall team, taking into account not only how many agents wanted to go in a particular direction, but the importance of that direction.
This is a dupe. Slashdot editors suck and should all be fired.
How would it rate the holocaust? Does it think the Nazi flag is an artistic masterpiece?
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
office? I was to add, ...in disgrace, but if course, he already is a disgrace. And that disgraceful staff, too -- LOCK THEM UP!
Ha-ha. Just kidding. Hannity will save them all, and the country, and the world.
Removing BeauHD's dupes
Wow!
Godwin in just one comment! I'm astonished.
Tay did nothing wrong!
By not modelling the actual game including the wonky, unreliable controllers and power supply related timing glitches and the host of other environmentals that runin your game just when it's getting interesting.
This was already posted only hours ago.
https://games.slashdot.org/sto...
They are developing AI to play video games? What a nice thing to waste money on. At least Watson is trying to cure people.
I hope they bought a licence for the game before they played it to death.
Software piracy is a problem...
"The AI pirated the software" is not an excuse.
Try Zelda II - Adventure of Link. I would kick its ass at that game.
This particular Atari game was one of the few games that resisted to Deep Q Learning (a form of Reinforcement Learning invented by DeepMind). Many researchers have tried over the last couple of years to solve it. This time, Microsoft found an ingenious solution to the problem, that combines experience from multiple agents and learns to form sub-goals. Their solution could mean that in the future it might be easier to apply reinforcement learning to other settings, such as robotics. The interesting part about reinforcement learning is that it learns dynamic behavior, as opposed to static classification. It learns to act in a way that mimics intelligence. This kind of machine learning is invaluable.
Shutting down free speech with violence isn't fighting fascism. It IS fascism!
But now I'm at peace with it.
#DeleteChrome
& raise you 2 hobbyist whiners from the overnet who can juggle digits in their sleep as needed... using genuine intelligence.. to solve genuine issues..
ManÃ(TM)s. Seriously. WTF?
This is like going to a doctors conference where everybody is a doctor except the speakers.
If you can't do the website in perl, don't do it in perl.
Don't fight for your country, if your country does not fight for you.
...UUUUUUUU... oh wait. Too late.
who programmed her? she acts hardwired... she's never been to cat school.. there's a digital gremlin in the codebase? she is conscious which machines are not... no heart no spirit no life...
Is this plugging the fact that they managed a perfect score in Ms. Pac-Man, or is this plugging that Microsoft has finally solved its middle-upper management problem and will be eliminating everyone from Satya Nadella on down to one level above their actually programmers, in order to help streamline and 'sanitize' Microsoft's development culture?
It is kind of crazy to task a computer to play a computer game. Perhaps we can figure out a way to do something more useful with computers one day, maybe something for people.
Do the writers of the AI think the AI enjoys computer games?
How do you know your cat is conscious?
How do I know you're conscious?
Fix your @â'ÂÎαμÏOE&©â(TM)¥encoding already!
Of course Google just a few weeks ago made a lot of buzz with AlphaGo ; *This* is an amazing achievement. And MS had to catch up! But Ms PM compared to AlphaGo ... well, not comparable.
Slashdot, fix the reply notifications... You won't get away with it...
FFS, does no-one on slashdot know how to encode text on the web? Does no-one give stories even the most cursory of proof reading?
Vice has recently reported that a university in Aachen, Germany, has created a database of play throughs that enable researchers to apply AI to Atari games.
The Canadians are doing good work in AI. There is an Alberta connection at Maluuba as well as a Waterloo connection. Note that Alberta heavily influenced development at DeepMind, as well.