The Epsilon-Greedy /UCB ("upper confidence bound") for MAB (Multiarmed-bandit) problem sometime in reinforcement learning (RL)
你是球队教练，现在突然要打一场比赛，手下空降三个球员，场上只能有一个出战，你不知道他们的能力，只能硬着头皮上，如何根据有限的上场时间看出哪个球员厉害，然后多让他上，从而得更多分数？
Epsilon-Greedy
supposed an k arm(slot) and set ε a little number between [0,0.1]
In short, epsilon-greedy means pick the current best option ("greedy") most of the time----(1-ε) + ε/k
but pick a random option with a small probability sometimes for other option-----(k-1)ε/k
often works as well as, or even better than, more sophisticated algorithms such as UCB
for more information about
A/B testing
Thompson sampling
see
