Theoretical foundations of reinforcement learning.
With Alekh Agarwal and John Langford.
Part of the Symposium on the Foundations of Computer Science, FOCS 2020.
Efficient contextual bandits with continuous actions.
Companion software for NeurIPS 2020 paper.
SLOPE experiments: continuous contextual bandits and reinforcement learning.
Companion software for ICML 2020 paper.
RL via State Decoding.
Companion software for ICML 2019 paper.
Large-scale Hierarchical Clustering.
Companion software for KDD 2017 paper.
Oracle-based Contextual Bandit Algorithms.
Companion software for semibandits, semiparametric CB, and CB model selection papers.
Nonparametric Estimators for Divergences.
Companion software for ICML14 and AISTATS15 papers.
Interactive Hierarchical Clustering.
Companion software for ICML12 paper.
Co-organized the Microsoft Reinforcement Learning Day, 2021.
Co-organized the Microsoft Reinforcement Learning Day, 2019.
Co-organized the Microsoft Reinforcement Learning Day, 2018.
Co-organized the ICML 2015 workshop on Advances in Active Learning.