Re:Pac-Man recreated with a GAN trained on 50k game episodes
by esoterica on Friday May 22, 2020 @03:09PM
(#23275749)
Do you really think nVidia is seriously advocating for using neural networks as the best way to write a PacMan clone? It's obviously just a proof of concept to demonstrate that GANs are sophisticated enough to learn certain categories of models.
[ Parent
| on HN ]
Re:Pac-Man recreated with a GAN trained on 50k game episodes
by robotresearcher on Friday May 22, 2020 @06:16PM
(#23277696)
Doing these cute demos is a double-edged sword. A fun and charming demo attracts attention by non-experts who can't see the wood for the trees.
In my field we make robots do a thing, say folding laundry, as an example of dextrous manipulation[1], and the popular conversation is about whether your laundry robot makes commercial sense and not about your novel grasping strategy and nifty motion planner that makes this sorta-possible for the first time. But everyone sees your video. Pros and cons.
[1] laundry folding at Berkeley (not me) https://youtu.be/gy5g33S0Gzo