This morning I got the usual update from arXiv (that’s a chi, not an X, folks!) with the list of newly uploaded manuscripts. Including this one:
Bandit Exploration
How could you not be interested?
Even better, this is how the abstract starts:
We consider the framework of stochastic multi-armed bandit problems and study the possibilities and limitations of strategies that explore sequentially the arms. The strategies are assessed not in terms of their cumulative regrets, as is usually the case, but through quantities referred to as simple regrets.
and it ends thus:
A concluding experimental study puts these theoretical bounds in perspective and shows the interest of nonuniform exploration of the arms.
I guess this is why bandits are so feared – they’re certainly not ‘armless.
