Randomized Allocation with Nonparametric Estimation for Contextual Multi-Armed Bandits with Delayed Rewards

2019/02/03 by Arya, Sakshi, Yang, Yuhong · 2 citations
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.1902.00819

Abstract

We study a multi-armed bandit problem with covariates in a setting where there is a possible delay in observing the rewards. Under some mild assumptions on the probability distributions for the delays and using an appropriate randomization to select the arms, the proposed strategy is shown to be strongly consistent.

Cited by

• Lipschitz Bandits with Stochastic Delayed Feedback
• Non-Linear Model-Based Sequential Decision-Making in Agriculture

Related

• Nonparametric Bandits with Covariates
• Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
• To update or not to update? Delayed Nonparametric Bandits with Randomized Allocation
• Multiarmed Bandit Problems with Delayed Feedback
• Contextual Linear Bandits with Delay as Payoff