80,000 Hours Podcast cover image

#48 - Brian Christian on better living through the wisdom of computer science

80,000 Hours Podcast

00:00

The Multi Arm Bandit Problem

In 19 50, bellman came up with his famous idea of dynamic programming. But in the context of the multi arm bandit problem, it relies on a few assumptions that make it not really ideal in practice. So we got the first really practical solution from kittens, i think, in the seventies or eighties. We now know it as the gitten's index - for every machine there is some price you would rather just take that reward again and again than even try the machine once.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app