Re:Give AI curiosity, and it will watch TV forever (2018)
by sdl on Wednesday January 31, 2024 @05:23PM
(#39210265)
I like the Bayesian Surprise definition for this. It's not about predicting the exact next state of the world (or the next frame of the noisy TV) but about how much the next state changes your model of the world.
https://papers.nips.cc/paper_files/paper/2005/hash/0172d289d...
This happens at all levels of sensory processing, from single cell firing (which is noisy) to the boredom you feel with a 100 channels of TV that are all technically novel to you but contain nothing remotely interesting.
Basically if you've built an agent that can be perpetually distracted by noise or a "noisy" TV then you've forgotten an important piece of the puzzle.