Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI Universe

universe.openai.com

Post reply on HN
Print view View original

81–90 of 139 posts

Re: OpenAI Universe

#81

Post by lawless123 »

BaronSamedi wrote: post #77
chongli wrote: post #73

Earlier quoted context omitted.

If your goal is to build General AI , getting access to the game state information is cheating and ultimately self defeating because it does not generalize across games. Expert humans are able to pick up and play a brand new game with a high degree of initial success despite zero knowledge of the memory states within the game. We do this by reliance on our vast knowledge of video game and literary tropes as well as e…

An AI which can learn any game from "looking" at a screen is a very ambitious goal. I doubt it is achievable in the near term. Humans can do it because of years of learning about the world. Personally, I prefer the more modest and achievable goal of teaching an AI to play complex real-time games such as Starcraft, LoL, and Dota--especially the latter 2 since they are team games.

That's not their goal though.They want AGI.

Re: OpenAI Universe

#82

Post by lawless123 »

BaronSamedi wrote: post #80
alkalait wrote: post #68

Earlier quoted context omitted.

Getting the game state data means deciding a-priori what features the AI should learn on. The whole point of the deep learning paradigm is to allow a machine to learn such features that enable good prediction, visualization, generation (aka. hallucination), etc. Instead, researchers have provided the raw feed input data to these agents with the hope that the learned features could be interpreted as game state data by…

I would say that it is a point of deep learning rather than "the whole point". For an AI to interact with the real-world then building models from vision (as we do) makes a lot of sense. In the virtual world, however, it makes no sense. Model data is already available and the AI has no need for something as inefficient as vision. We humans have to use vision (and sound, etc) in games because we have do not have acces…

If they want their AGI to applicable to the real world or software with incomplete or insufficient APIS they have to do it the way they are doing it here.

There isn't an API for me to check if i'm still on the foot path and not the road as i walk down the street.

I can't use an API to tell me water is boiling and that i shouldn't stick my hand in it.

Re: OpenAI Universe

#83

Post by OliverD »

llSourcell wrote: post #21

Hey guys, it's Siraj. OpenAI asked me to make a promotional video for it on my Youtube channel and I gladly said yes! You can check it out here: https://www.youtube.com/watch?v=mGYU5t8MO7s

Awesome Video! You just got yourself a new subscriber :)

Re: OpenAI Universe

#84

Post by gwern »

mtgx wrote: post #67
BaronSamedi wrote: post #65

Unless I missed something it looks like the AI has to learn from screen pixels instead of getting game state data. I don't like that approach at all. I understand that it's easy to implement for OpenAI but I think having the game developers provide a real bot-capable API is much better. I hope the latter is what Blizzard will provide for their DeepMind collaboration.

Seems unlikely. The focus seems to be on improving AI through "vision". The idea is to make the AI learn skills the same way a human would (at least in the first years of life). Google's AlphaGo also learned from screen pixels. So these would be human-like bots, rather than bot-like bots, like you normally have in games. The bot would simply learn by doing, until it masters the game, not by getting access to game alg…

> Google's AlphaGo also learned from screen pixels.

It did not. It received the state of the board as one array, another board state array for capture/komi (since Go does have global state which is not visible purely from the board representation), and a few additional features to help it out with stuff like ladders. It was architected with convolutional layers, but over the Go grid, not pixels. See the AlphaGo paper pg11 for the exact structure of the input: http://www.postype.com/files/2016/04/08/16/05/03384c91046e8e...

Could it have learned from pixels (augmented by the additional necessary global state)? Sure. But that would've been a waste of computation since the visual layout of a Go board is fixed and static, unlike Atari games.

Re: OpenAI Universe

#85

Post by hacker_9 »

d_burfoot wrote: post #71

Disclaimers: I cannot see the future. These are just my opinions. I really appreciate the work and money that SamA, Elon, and others have put into the OpenAI project. The Universe work in particular might help encourage young people, many of whom love video games, to study AI. But I feel that contrarians, such as myself, have an ethical commitment to young people to voice our doubts and criticisms, so that they can a…

"Deep Learning, as it is practiced, isn't intellectually deep. With a few exceptions, there is nothing comparable to the great discoveries of physics ... Progress in DL mostly comes from architecture hacking: tweak the network setup, run the training algo, and see if we get a better result."

To be fair isn't this what physicists do all day at CERN too? Smash some particles together, analyse the numbers, try to find patterns, tweak a few things and try again?

Re: OpenAI Universe

#86

Post by zardo »

cing wrote: post #16

End game; I'd really like an AI agent for "in real life" tabletop games (like boardgames).

Tabletop simulator would making an interesting training environment. I may not be able to train a good go player, but a table flipping sore loser is probably doable.

Re: OpenAI Universe

#87

Post by pakl »

d_burfoot wrote: post #71

Disclaimers: I cannot see the future. These are just my opinions. I really appreciate the work and money that SamA, Elon, and others have put into the OpenAI project. The Universe work in particular might help encourage young people, many of whom love video games, to study AI. But I feel that contrarians, such as myself, have an ethical commitment to young people to voice our doubts and criticisms, so that they can a…

What you mention in point #1 isn't the main issue with games, but with the "reactive" approach in AI. Reactive AI systems are necessarily going to be more limited than say, predictive AI systems (a new emerging class of AI models). [1]

Agreed, though, that the focus on games is a long-standing source of problems holding back AI. My colleague has referred to this as "ludic AI" in a recent blog post where he expands on your statement about the real challenge of intelligence. [2]

[1] Reactive vs Predictive AI (http://blog.piekniewski.info/2016/11/03/reactive-vs-predicti...)

[2] Learning Physics (http://blog.piekniewski.info/2016/11/30/learning-physics-is-...)

Re: OpenAI Universe

#88

Post by pakl »

hacker_9 wrote: post #85
d_burfoot wrote: post #71

Disclaimers: I cannot see the future. These are just my opinions. I really appreciate the work and money that SamA, Elon, and others have put into the OpenAI project. The Universe work in particular might help encourage young people, many of whom love video games, to study AI. But I feel that contrarians, such as myself, have an ethical commitment to young people to voice our doubts and criticisms, so that they can a…

"Deep Learning, as it is practiced, isn't intellectually deep. With a few exceptions, there is nothing comparable to the great discoveries of physics ... Progress in DL mostly comes from architecture hacking: tweak the network setup, run the training algo, and see if we get a better result." To be fair isn't this what physicists do all day at CERN too? Smash some particles together, analyse the numbers, try to find p…

I take the point to be that there aren't "deeper" fundamental principles at play in these models. Tremendous progress has comes from simply tweaking of the numbers of layers, or how the feed forward to each other (skipping layers, etc), or by throwing more computer power or data at the same basic algorithm.

Where might we look for deeper principles? One idea is to consider what brains do and how they might be doing it. (I'm not saying we need to go down the rabbit hole of biological detail -- on the contrary I'm suggesting we look at known or even hypothesized principles of brain operation and import them into AI.)

Two ideas we have used in our work: prediction (over time), recurrent feedback (most brain regions have more feedback than feedforward inputs)

Re: OpenAI Universe

#89

Post by pakl »

state_less wrote: post #63

I'd love to see AI, using games, master the art of determining a depth for objects in the scene. If you ask a person, "about how far away is that car?", they often give you an okay answer that is at least in the same magnitude as the actual distance 1 m, 10 m, 100 m, 1000 m. If AI could do that, you could then navigate an environment in the real world better using only a camera or two. So you start with a virtual wor…

That's a great (and hard) problem!

More generally, imagine AI that could learn the physics of the world. For example, if the ball is rolling away, the AI should be able to predict that the ball will look smaller on the next frame.

Going further, if the ball is about to roll under a shadow, the AI should predict that the ball will become a darker shade of green.

(After several years working in a robotics research company, these kinds of capabilities are exactly what we determined would be necessary for robot AI.)

Re: OpenAI Universe

#90

Post by noobermin »

state_less wrote: post #76
d_burfoot wrote: post #71

Disclaimers: I cannot see the future. These are just my opinions. I really appreciate the work and money that SamA, Elon, and others have put into the OpenAI project. The Universe work in particular might help encourage young people, many of whom love video games, to study AI. But I feel that contrarians, such as myself, have an ethical commitment to young people to voice our doubts and criticisms, so that they can a…

1. Games are great, especially the closer they get to the real 3d worlds with all the basic visual transforms in play. You can generate training data cheaper that helps you bootstrap the AI. 2. Your argument, which boils down to large organizations can accomplish more than individuals is in general true. But then that isn't saying anything new. Still, I'd prefer the car company give its blueprints than not. My factor…

> The insight that we simplify AI architecture to some addition and multiplication is a big idea - in my opinion

Multi-linear fitting is an insight? Perhaps it's application to certain problems is. That might be what you mean.

Post reply on HN