Skip to yearly menu bar Skip to main content


Design of Experiments for Stochastic Contextual Linear Bandits

Andrea Zanette · Kefan Dong · Jonathan N Lee · Emma Brunskill

Keywords: [ Reinforcement Learning and Planning ] [ Bandits ]


In the stochastic linear contextual bandit setting there exist several minimax procedures for exploration with policies that are reactive to the data being acquired. In practice, there can be a significant engineering overhead to deploy these algorithms, especially when the dataset is collected in a distributed fashion or when a human in the loop is needed to implement a different policy. Exploring with a single non-reactive policy is beneficial in such cases. Assuming some batch contexts are available, we design a single stochastic policy to collect a good dataset from which a near-optimal policy can be extracted. We present a theoretical analysis as well as numerical experiments on both synthetic and real-world datasets.

Chat is not available.