We propose a model for learning with bandit feedback while accounting fo...
We investigate the optimal design of experimental studies that have
pre-...
In many sequential decision-making problems, the individuals are split i...
We characterize Bayesian regret in a stochastic multi-armed bandit probl...
We consider non-parametric estimation and inference of conditional momen...
In this paper we develop new methods for estimating causal effects in
se...
The contextual bandit literature has traditionally focused on algorithms...
Recurrent neural networks have been very successful at predicting sequen...