Some designers from Stripe absolutely helped with the design of this page.
OpenAI Universe
131–139 of 139 posts
Re: OpenAI Universe
#132Hey 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
very boring and predictable one. "whayyy, very cool, more, bigger, better, whayyyy".
Re: OpenAI Universe
#133This is astounding! If requests are being taken, it would be useful to be able to search through the listed environments. And a poker environ for the internet section would be a good balance of fun, widely appreciable and a straight forward but very non-trivial environment.
you'll lose your job and will be replaced by AI. Astounding?
Re: OpenAI Universe
#134Hey 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
Nice video, but the jump from solving super simple 2d games, by feedback of binary win/lose conditions, to solving tasks in 3d open world simulations will require an un-imaginably gigantic leap in processing and knowledge. Additionally neural nets have already shown they are not sufficiently good enough at generalizing, and only work well at the specific tasks they were trained for. So the idea that an AI that can pl…
I'm far from an expert, but I thought the poor generalized performance of neural nets was largely associated with the complexity of the network (number of neurons, etc), and the training data.
Is there something more specific about the application of neural nets to generalized problems that makes them unsuitable?
Re: OpenAI Universe
#135jesus man the constant switching of inflection due to jump cuts and shitty jokes was irritating. This is the stuff I always hate about your videos, and in general any "how to code an AI that does ___ with only < 10 lines of python". No you're giving me an extremely generic framework, and some vague direction that i can read off the linked page (the 9 lines), not how to actually write all these things, those are like…
I bet you have some far superior videos for your own open source projects--why don't you post links to those babies so we can learn how to do it right?
I never made that argument.
I made the argument that nearly every single one of this guy's videos are not the least bit helpful in actually learning how machine learning works, and gets viewed based on click-baity title and click-bait thumbnails (attractive girls a lot of the time). Which i will stand by. Every one of them is "how to write an AI that ___" when its importing tensorflow, setting 2-3 hyper parameters then letting it run.
Re: OpenAI Universe
#136Earlier quoted context omitted.
In a sense, I would say yes there are learning laws, but it's still early in codifying them. Along one axis, you could compare: supervised, semi-supervised, self-supervised and unsupervised learning. Along another axis, consider that there are versions of each method that take into account temporal/dynamic data, versus others that require randomly shuffled static data. In the current problems of visual perception, I…
>In the current problems of visual perception, I think the field would benefit greatly a shift to focus on multiscale interaction/dynamics rather than on (static) statistics as it is currently (for more on this, see my colleague's blog: [1]). Your friend's blog has a lot of good insights that I've seen in the theoretical neuroscience and computational cognitive science literature as well. Where do you guys work?
I work at LeEco US out of San Diego, and my colleagues work at other ML/AI companies also in San Diego. We originally met and collaborated at Brain Corporation.
Re: OpenAI Universe
#137Being able to "Infer" from what it learns and "Apply" it to new scenarios in a general way is all about intelligence. I do not see how making it to win one game or one million will move it towards achieving general intelligence of this sort.
Re: OpenAI Universe
#138Earlier quoted context omitted.
> Google's AlphaGo also learned from screen pixels. Source? That literally seems to make zero sense to me. Go can be represented in a super-simple state. Why make it spend millions of cycles learning to categorize pixels into that state you already have?
I would guess that they trained AlphaGo from many thousands of hours of match footage. Writing a computer vision script to segment / extract the data may cost cycles as you say, but would save many human hours by eliminating the need to re-watch the footage and literally type out state information for each move.
Again, that doesn't make sense because the moves have almost certainly already been typed out by somebody. It's the same in chess. There are databases containing millions of games.
Re: OpenAI Universe
#139What is state of the art in reinforcement learning right now? https://arxiv.org/abs/1602.01783 Is there a way to deal with "sparse" training data (state, action, reward) triples -- sparse in "state"?
That paper was 10 months ago. There have been many RL papers in the meantime, but sparsity is only a problem with respect to reward, not state or action, from what I can see.
You didn't answer my question. :(