research
∙
05/09/2022
Selectively Contextual Bandits
Contextual bandits are widely used in industrial personalization systems...
share
research
∙
06/03/2021
Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning
Empirical risk minimization (ERM) is the workhorse of machine learning, ...
research
∙
06/01/2021
Post-Contextual-Bandit Inference
Contextual bandit algorithms are increasingly replacing non-adaptive A/B...
research
∙
02/25/2021
Doubly-Adaptive Thompson Sampling for Multi-Armed and Contextual Bandits
To balance exploration and exploitation, multi-armed bandit algorithms n...
research
∙
01/18/2021
Sequential causal inference in a single world of connected units
We consider adaptive designs for a trial involving N individuals that we...
research
∙
07/22/2019
Doubly robust off-policy evaluation with shrinkage
We design a new family of estimators for off-policy evaluation in contex...
research
∙
12/15/2018
Balanced Linear Contextual Bandits
Contextual bandit algorithms are sensitive to the estimation method of t...
research
∙
05/23/2018
Scalable Coordinated Exploration in Concurrent Reinforcement Learning
We consider a team of reinforcement learning agents that concurrently op...
research
∙
02/05/2018
Coordinated Exploration in Concurrent Reinforcement Learning
We consider a team of reinforcement learning agents that concurrently le...
research
∙
11/19/2017