Jump to content

Welcome to FutureTimeline.forum
Register now to gain access to all of our features. Once registered and logged in, you will be able to create topics, post replies to existing threads, give reputation to your fellow members, get your own private messenger, post status updates, manage your profile and so much more. If you already have an account, login here - otherwise create an account for free today!

These ads will disappear if you register on the forum

Photo

OpenAI beats team of top humans at Dota 2


  • Please log in to reply
6 replies to this topic

#1
funkervogt

funkervogt

    Member

  • Members
  • PipPipPipPipPip
  • 348 posts

Another milestone:

 

At an event in San Francisco on Sunday, a team ranked in the 99.95th percentile faced off against OpenAI Five, OpenAI‘s eponymous game-playing AI, and won just one match in a series of three.

 
...Months ago, when OpenAI kicked off training, the AI-controlled Dota 2 heroes “walked aimlessly around the map.” But it wasn’t long before the AI mastered basics like lane defense in farming, and soon after, it nailed advanced strategies like rotating heroes around the map and stealing items from opponents.
 
Later this month, OpenAI plans to square OpenAI Five off against Dota 2 players at Valve’s eighth annual The International esports competition.

https://venturebeat....l-dota-players/


  • Yuli Ban and starspawn0 like this

#2
Raklian

Raklian

    An Immortal In The Making

  • Moderators
  • PipPipPipPipPipPipPipPipPipPip
  • 6,753 posts
  • LocationRaleigh, NC

Now it's a matter of AI competing with another AI to determine which one is the better one.

 

Humans are being left in the dust... maybe forever (for natural humans, that is).


  • Yuli Ban likes this
What are you without the sum of your parts?

#3
funkervogt

funkervogt

    Member

  • Members
  • PipPipPipPipPip
  • 348 posts

Any bets on how long it will be until an AI wins the Starcraft 2 world championship? 


  • Yuli Ban likes this

#4
Raklian

Raklian

    An Immortal In The Making

  • Moderators
  • PipPipPipPipPipPipPipPipPipPip
  • 6,753 posts
  • LocationRaleigh, NC

Any bets on how long it will be until an AI wins the Starcraft 2 world championship? 

 

This year or the next.


  • Yuli Ban likes this
What are you without the sum of your parts?

#5
Outlook

Outlook

    Arab Muslim

  • Members
  • PipPipPipPipPipPip
  • 775 posts
  • LocationBarbary Lands
Can't wait till the AI explains how.
  • Yuli Ban likes this

The Prophet (saw) said: He who does not thank the people is not thankful to Allah.


#6
starspawn0

starspawn0

    Member

  • Members
  • PipPipPipPipPipPip
  • 505 posts
I posted one of Greg Brockman's tweets right after the win under the "AI & Robotics News and Discussions" section.

I don't know enough about Starcraft 2 to make an informed bet -- if I knew more about it, I could probably give a good estimate.

The days of humans winning at games that can be fully simulated, are numbered. These training methods are highly scalable.

More impressive, by far, was OpenAI's recent dexterous robot hand work. The system was trained entirely in simulation, and then worked on real world robots. In fact, they first tried to mix real-world training data with simulated data, and it didn't help -- so they went with 100% simulated, and it worked beautifully on real-world robots! The key was doing the right kinds of randomization so that learning in simulation transfers to the real world. They've said that, in the future, they'd like to automate that part, too, so that the types of randomizations are chosen entirely by the machine.

That's the kind of thing that has a real chance of making home robots feasible -- especially given the rate of increase in compute being thrown at the largest AI projects (it grows by 10x every year!), and especially since there are now some pretty realistic home robot environments to train them in. Training probably won't just be "throw the robot in the environment, and see if it fails anywhere along the way"; it's probably going to have to be made up of a hierarchy of things -- but it's still probably doable near-term, in simulation -- and then also the real world, if those randomizations work as well on such a complicated task.

I would guess that mathematical theorem-proving and programming contest-level programming might also -- somehow -- succumb to these methods. This "world" can be simulated; what's missing is a way to generate a set of "natural" things to prove. Proving random things will not do; humans don't prove random things.

But none of this is going to make Turing Test-passing AIs. That's a different beast, and will require a much different set of approaches. BCIs + DL are our best chance; Big Data + DL + (statistical algorithms) might also work, but at a slower pace of development.

#7
starspawn0

starspawn0

    Member

  • Members
  • PipPipPipPipPipPip
  • 505 posts
Just the other day Richard Socher (Salesforce's AI chief) Tweeting some things that are relevant to the last part of what I wrote above (basically saying some of the same things):


https://mobile.twitt...529260775694339
 

Prediction: Any AI problem that you can simulate and sample endlessly many training samples for can be solved with today's algorithms such as deep and reinforcement learning.


https://mobile.twitt...750869839073280


Just because it doesn't apply to every problem doesn't make it meaningless. It also doesn't apply to language understanding because we cannot simulate language. Which is why techniques that have this requirement probably won't get us there.


I disagree with the first thing he said -- but think it will work with lots of important problems -- I do agree with the second thing he said here.
  • Casey likes this




0 user(s) are reading this topic

0 members, 0 guests, 0 anonymous users