Search Results for author:
Found 4 papers, 0 papers with code
Thompson Sampling for Parameterized Markov Decision Processes with Uninformative Actions
We study parameterized MDPs (PMDPs) in which the key parameters of interest are unknown and must be learned using Bayesian inference.
A data-driven approach to beating SAA out-of-sample
While solutions of Distributionally Robust Optimization (DRO) problems can sometimes have a higher out-of-sample expected reward than the Sample Average Approximation (SAA), there is no guarantee.
Worst-case sensitivity
We introduce the notion of Worst-Case Sensitivity, defined as the worst-case rate of increase in the expected cost of a Distributionally Robust Optimization (DRO) model when the size of the uncertainty set vanishes.
Calibration of Distributionally Robust Empirical Optimization Models
Building on the intuition that robust optimization reduces the sensitivity of the expected reward to errors in the model by controlling the spread of the reward distribution, we show that the first-order benefit of ``little bit of robustness" (i. e., $\delta$ small, positive) is a significant reduction in the variance of the out-of-sample reward while the corresponding impact on the mean is almost an order of magnitude smaller.
