 Almost Optimal Variance-Constrained Best Arm IdentificationIEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2022 |
 A Unifying Theory of Thompson Sampling for Continuous Risk-Averse
BanditsAAAI Conference on Artificial Intelligence (AAAI), 2021 Joel Q. L. Chang Vincent Y. F. Tan |
 Off-Policy Risk Assessment in Contextual BanditsNeural Information Processing Systems (NeurIPS), 2021 |
