Skip to content

Latest commit

 

History

History
40 lines (32 loc) · 1.4 KB

1f59b2e1.md

File metadata and controls

40 lines (32 loc) · 1.4 KB
title slug tags date
Multi-armed Bandit Problem
multi-armed-bandit-problem
zettel
multi-armed-bandit-problem
statistics
probability
mathematics
computer-science
algorithms-to-live-by
book
book/algorithms-to-live-by
brian-christian
tom-griffiths
brian-christian-and-tom-griffiths
2022-01-27T07:24

wide

In Computer Science, one of the most popular problem in the realm of [[04f52b1f|Explore-exploit trade-off]] is the Multi-armed bandit problem. The term derived from the casino slot machine "one-armed bandit", and as the name suggests, the problem entails multiple slot machines and how to win as much as possible.1

The real problem, however, is getting an idea of the odds of each slot machine to know when to keep playing or move on to the next one.

Multi-Armed Bandits: A Cartoon Introduction - DCBA #12

<iframe width="100%" height="315" src="https://www.youtube.com/embed/bkw6hWvh_3k" frameborder="0" allow="autoplay;encrypted-media" allowfullscreen></iframe>

Footnotes

  1. Algorithms to Live By by Brian Christian and Tom Griffiths - Explore/Exploit

  2. https://www.youtube.com/watch?v=bkw6hWvh_3k&ab_channel=AcademicGamer (Multi-Armed Bandits: A Cartoon Introduction - DCBA)