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

Pac-Man recreated with a GAN trained on 50k game episodes

blogs.nvidia.com

Post reply on HN
Print view View original

141–150 of 154 posts

Re: Pac-Man recreated with a GAN trained on 50k game episodes

#141

Post by collyw »

lumost wrote: post #70

I've observed an increasing trend with modern AI research that A) It's no longer practical to incorporate into real products given the hardware costs for training and inference. In NLP, large transformer based models can easily occupy a 5 thousand dollar GPU at a paltry 50-60 words per second processing pace. B) The Research often demonstrates things that existing non-ML toolchains were already reasonable at doing wi…

"This demo looks like it's replicated the core mechanics of pac-man with worse graphics, 3-4 orders of magnitude higher resource consumption, and undoubtably many odd bugs hidden away from the pretty demo. It even needed the game to exist in the first place!"

True, though my first thought was that this would be interesting from a reverse engineering point of view. Then again Pacman is pretty simple concept. Something worth reverse engineering is probably a lot more complex.

Re: Pac-Man recreated with a GAN trained on 50k game episodes

#142

Post by collyw »

bobly_today wrote: post #128
101404 wrote: post #126

Earlier quoted context omitted.

Because it's a pile of if-else statements shuffled until it was able to perform a single specialized thing. Any housefly would by a thousand times as "conscious".

What makes you so certain a house fly doesn’t have a form of rudimentary consciousness? It might be a spectrum.

I assume that a housefly does have a basic form of consciousness. It's not going to write Shakespeare but it probably wants to mate. (I know people who's life goals don't appear to extend much further).

Re: Pac-Man recreated with a GAN trained on 50k game episodes

#143

Post by collyw »

itchyjunk wrote: post #8

Thought experiment: Is my brain also generating reality without a physics engine and is filling in details that it thinks should be there? If true, what are the advantages/disadvantages of it?

Yes. Many optical illusions will prove that. Or try some Psychedelics. I assume its beneficial for survival.

Re: Pac-Man recreated with a GAN trained on 50k game episodes

#144

Post by ekianjo »

__s wrote: post #15
ekianjo wrote: post #13

> Trained on 50,000 episodes of the game Meanwhile an actual human will probably need only about 5 games to fully understand how the game works and reacts.

I wouldn't say "fully" https://www.gamasutra.com/view/feature/3938/the_pacman_dossi... & also that humans come with a huge amount of training beforehand. We've experienced eating & ghost stories & moving around in 3d spatial dimensions before playing pacman usually

Not a very convincing argument. Even when Pac man was new and video games barely existed it took no time to get how it works.

Re: Pac-Man recreated with a GAN trained on 50k game episodes

#145

Post by ekianjo »

c1b wrote: post #118
ekianjo wrote: post #13

> Trained on 50,000 episodes of the game Meanwhile an actual human will probably need only about 5 games to fully understand how the game works and reacts.

and how many games does a human need to transform into a pacman game playable by another human? ...lol

The same. Once you understand how it works its just about coding. Coding Tetris never required anyone to play millions of times either.

Re: Pac-Man recreated with a GAN trained on 50k game episodes

#146

Post by ekelsen »

fpgaminer wrote: post #96
lumost wrote: post #70

I've observed an increasing trend with modern AI research that A) It's no longer practical to incorporate into real products given the hardware costs for training and inference. In NLP, large transformer based models can easily occupy a 5 thousand dollar GPU at a paltry 50-60 words per second processing pace. B) The Research often demonstrates things that existing non-ML toolchains were already reasonable at doing wi…

> It's no longer practical to incorporate into real products given the hardware costs for training and inference I don't see that trend. Bleeding edge research has always been beyond what's practical, by its very nature. The focus is on pushing the boundaries, not to build something efficient/commercial. It's the followup work that makes it practical. See for example the evolution of WaveNet. It was breakthrough rese…

One minor nit: The recent FB blogpost wasn't really "research" - it was mostly a reimplementation of this paper: https://arxiv.org/abs/1802.08435

Re: Pac-Man recreated with a GAN trained on 50k game episodes

#147

Post by angel_j »

lumost wrote: post #132
angel_j wrote: post #131

Earlier quoted context omitted.

Followed by decades long monopoly over expensive new technology, likely crushing waves of innovation and usage, in exchange for slow, buggy, not-even-automated spreadsheets; plus the hemming of governments and organizations into endless software rental contracts and platforms, that maybe don't add value as fast as Moore's Law.

that's a fair criticism, however it's not a given that any product category will end up with the same growth curve of PCs, the web, cloud, and mobile. thinking back on the PC, Web, cloud, and mobile growth periods, each came with a transformative change in the capabilities, cost, and availability of computing power. We're only seeing two of these aspects in AI today - with the cost side heading in the wrong direction…

AI supercharged the importance of computing power to arms-race levels. We're still just brute forcing it with Deep Learning, but the capabilities are too awesome to ignore. Therefore, compute power will be bought-up and hoarded expensively, and used on the highest bidder. Will the market save us, and simply over-clock production? Not happening yet. Corporate appetite should be quite large. I do A.I. R&D and am just watching the mountain of power ascend before me and aged gaming laptop. My next level is yet the foothills. Yeah, I'd say growth or not, A.I. is going where PC, web, cloud, everything, goes, to the industrial monopolists and the money spenders.

Re: Pac-Man recreated with a GAN trained on 50k game episodes

#149

Post by ccvannorman »

This seems less impressive than the Mario recreation from a few years ago[0] -- I must be missing something because this is a simpler game that was trained on significantly more data, yet the result is comparatively worse.

[0] https://www.theverge.com/2017/9/10/16276528/ai-video-games-g...

Re: Pac-Man recreated with a GAN trained on 50k game episodes

#150

Post by lumost »

angel_j wrote: post #147
lumost wrote: post #132

Earlier quoted context omitted.

that's a fair criticism, however it's not a given that any product category will end up with the same growth curve of PCs, the web, cloud, and mobile. thinking back on the PC, Web, cloud, and mobile growth periods, each came with a transformative change in the capabilities, cost, and availability of computing power. We're only seeing two of these aspects in AI today - with the cost side heading in the wrong direction…

AI supercharged the importance of computing power to arms-race levels. We're still just brute forcing it with Deep Learning, but the capabilities are too awesome to ignore. Therefore, compute power will be bought-up and hoarded expensively, and used on the highest bidder. Will the market save us, and simply over-clock production? Not happening yet. Corporate appetite should be quite large. I do A.I. R&D and am just w…

I work in industrial AI research as well, but I think it's worth considering whether AI is providing an incremental benefit on existing products through the use of imense computing power - or unlocking new demand through new applications. If the latter category is limited by available compute, then we'll reach the limits of economically viable use cases rather quickly without the aid of moore's law.
Post reply on HN