Live data from Hacker News

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

blogs.nvidia.com

11–20 of 154 posts

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

#11
post #9

Interesting to explore how this can be used. You still need to develop a game with an actual engine first, to generate all the samples for training the AI how to generate frames without an engine. But maybe if training sample size can be considerably reduced, game making can open up to far less technical people. Instead of developing with an engine, game makers could show the AI "when I press this button, change the…

Programming then becomes teaching.

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

#14
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.

Fundamentally, this is because we have already been trained on years of living in and reacting to the real world, which, to some abstract degree, the game mimicks. The Nvidia model starts with nothing.

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

#15
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

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

#16
This research reminds me of one of their April Fool’s videos [1] with a gaming USB stick that you plug into your computer to offer various gaming enhancements. One of which is a “Ghostplay” feature where an AI program can mimic you after training on your gameplay.

I remember that video because it always struck me as not being far off from reality. It’ll make the current set of online game cheats/hacks seem like child’s play if it can be done effectively (read: human-like and undetectable). Maybe then a server-running AI will be needed to detect AI-like gameplay mimicry.

[1] https://youtu.be/smM-Wdk2RLQ

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

#17
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 think a few more.

Early games will establish things like "can ghosts go through each other", "if I hit the wall do I die" (like in Snake; though on Acorn Electron you could eat the wall sometimes!), "can ghosts go through the shortcut", "how long do pills last", do all pills last the same amount of time".

Then later efforts would be needed to know things like "what algorithm do the ghosts follow", "does the same colour ghost always follow the same algo", "do ghost algos change when you eat a fruit", "what order do the fruit go in" ...

Of course you could guess a lot of these, but that's not what "fully understand how the game works" means.

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

#20

This research reminds me of one of their April Fool’s videos [1] with a gaming USB stick that you plug into your computer to offer various gaming enhancements. One of which is a “Ghostplay” feature where an AI program can mimic you after training on your gameplay. I remember that video because it always struck me as not being far off from reality. It’ll make the current set of online game cheats/hacks seem like child…

Servers are already running AI to try and counter cheating in quite a few games.
Post reply on HN