LGAug 13, 2015
A Survey on Contextual Multi-armed Bandits
arXiv:1508.03326v2141 citations
AI Analysis
This is an incremental survey paper for researchers in reinforcement learning and decision-making.
This survey paper reviews stochastic and adversarial contextual bandit algorithms, analyzing their assumptions and regret bounds.
In this survey we cover a few stochastic and adversarial contextual bandit algorithms. We analyze each algorithm's assumption and regret bound.