no code implementations • 13 May 2023 • Michael Gimelfarb, Michael Jong Kim
We study parameterized MDPs (PMDPs) in which the key parameters of interest are unknown and must be learned using Bayesian inference.
no code implementations • 26 May 2021 • Jun-Ya Gotoh, Michael Jong Kim, Andrew E. B. Lim
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.
no code implementations • 21 Oct 2020 • Jun-Ya Gotoh, Michael Jong Kim, Andrew E. B. Lim
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.
no code implementations • 17 Nov 2017 • Jun-Ya Gotoh, Michael Jong Kim, Andrew E. B. Lim
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.