Publications
7 results found
Li X, Sun C, Ye Y, 2022, Simple and Fast Algorithm for Binary Integer and Online Linear Programming, Neural Information Processing Systems
Li X, Ye Y, 2021, Online linear programming: dual convergence, new algorithms, and regret bounds, Operations Research, ISSN: 0030-364X
Li X, Zhong H, Brandeau M, 2020, Quantile Markov decision process, Publisher: Institute for Operations Research and Management Sciences
The goal of a traditional Markov decision process (MDP) is to maximize expected cumulative reward over a defined horizon (possibly infinite). In many applications, however, a decision maker may be interested in optimizing a specific quantile of the cumulative reward instead of its expectation. In this paper we consider the problem of optimizing the quantiles of the cumulative rewards of a Markov decision process(MDP), which we refer to as a quantile Markov decision process (QMDP). We provide analytical results characterizing the optimal QMDP value function and present a dynamic programming-based algorithm to solve for the optimal policy. The algorithm also extends to the MDP problem with a conditional value-at-risk(CVaR) objective. We illustrate the practical relevance of our model by evaluating it on an HIV treatment initiation problem, where patients aim to balance the potential benefits and risks of the treatment.
Li X, Zhang X, Zheng Z, 2018, DATA-DRIVEN RANKING AND SELECTION: HIGH-DIMENSIONAL COVARIATES AND GENERAL DEPENDENCE, 2018 Winter Simulation Conference (WSC), Publisher: IEEE
Zhong H, Li X, Lobell D, et al., 2018, Hierarchical modeling of seed variety yields and decision making for future planting plans, Environment Systems and Decisions, Vol: 38, Pages: 458-470, ISSN: 2194-5403
Zhou Z, Li X, Zare R, 2017, Optimizing Chemical Reactions with Deep Reinforcement Learning, ACS Central Science, ISSN: 2374-7943
Li C, Li X, 2015, A closed-form expansion approach for pricing discretely monitored variance swaps, Operations Research Letters, ISSN: 0167-6377
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.