News for hackers. Stuff that matters.
Re:Reinforcement Learning – Bandit Problems by noelwelsh on Monday May 07, 2018 @10:10AM (#17012842)
Adding new arms in a bandit problem doesn't pose a problem for most bandit algorithms. Any of the common algorithms will handle it just fine. Arms disappearing is more interesting, as that effects the explore / exploit tradeoff. It's been a while since I was studying bandit algorithms but "Mortal multi-armed bandits" is one paper that addresses this.

There are no comments on this comment yet.