"Joint preference estimation and robust optimization" (with Junjie Lei, Yanyu Lu, Erick Delage and Zuo-Jun Max Shen), to be submitted, 2026.
"Stabilizing CVaR risk-aware Q-Learning through modular adaptive training mechanisms" (with Yifan Wu and Junjie Lei), to be submitted, 2026.
"Fast convergent risk-aware reinforcement learning" (with Junjie Lei, Dionysios Kalogerias and Zuo-Jun Max Shen), to be submitted to Journal of Machine Learning Research, 2026.
"Optimal partial centralization under decentralized self-selection and processing bottlenecks" (with Xiaobo Li, Yinuo Lin and Lei Xu), under review, Manufacturing & Service Operations Management, 2026.
"A unified minimax framework for online non-convex long-term constrained optimization" (with Shijie Pan and Jianyu Xu), under review, Journal of Artificial Intelligence Research, 2026.
"Robust assortment optimization under nested logit model" (with Yicheng Liu and Zizhuo Wang), under major revision, Operations Research Letters, 2026.
"The role of mixed discounting in risk-averse sequential decision-making" (with Erick Delage and Shanshan Wang), R&R, Management Science, 2025.
"Efficiently computing the quasi-concave envelope with incomplete information" (with Jian Wu, William B. Haskell and Huifu Xu), under 2nd round review, SIAM Journal on Optimization, 2026.
"Shaping sparse rewards in reinforcement learning: A semi-supervised approach" (with Wenyun Li and Chen Sun), IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), 2026.
"DRL-ORA: Distributional reinforcement learning with online epistemic risk adaptation" (with Yupeng Wu, Wenyun Li and Chin Pang Ho), Conference on Uncertainty in Artificial Intelligence (UAI), 2026. [acceptance rate: 30.5%]
"Robust data-driven quasi-concave optimization" (with Jian Wu, William B. Haskell and Huifu Xu), INFORMS Journal on Computing, 2026. [Preprint][Code]
"Assortment planning under spectral risk measures" (with Junjie Lei and Zizhuo Wang), European Journal of Operational Research, 2026. [Supplemental Materials][Preprint]
"Preference robust optimization for choice functions on the space of CDFs" (with William B. Haskell and Huifu Xu), SIAM Journal on Optimization, 2022. [Preprint]
"Randomized smoothing variance reduction method for large-scale non-smooth convex optimization" (with Xun Zhang), Operations Research Forum, 2021.[Supplemental Materials]
"Model and reinforcement learning for Markov games with risk preferences" (with Viet Hai Pham and William B. Haskell), AAAI Conference on Artificial Intelligence (AAAI), 2020. [Supplemental Materials][acceptance rate: 20.6%]
"Stochastic approximation for risk-aware Markov decision processes" (with William B. Haskell), IEEE Transactions on Automatic Control, 2020. [Supplemental Materials]
"Data-driven satisficing measure and ranking", Journal of the Operational Research Society, 2019. [Preprint]
"Risk-aware Q-learning for Markov decision processes" (with William B. Haskell), IEEE Conference on Decision and Control (CDC), 2017.
"Large-scale optimization for non-parametric ranking under high-order risk preferences" (with Kai Tu and Man-Chung Yue), Work-in-Progress.
"Contextual and active preference robust optimization" (with Erick Delage and Zuo-Jun Max Shen), Work-in-Progress.
"Online joint pricing and capacity allocation under risk-aware retailer" (with Youxin Wang and Wenhan Lu), Work-in-Progress.
"Empirical target-based dynamic programming" (with Shijie Pan, Xudong Wu, Jiayu Chen and Qixiu Cheng), Work-in-Progress.
"Exploiting transitivity structure in online ranking via pairwise comparisons" (with Ethan Hao Feng Lam, Alec Kirkley and Sebastian Morel-Balbi), Work-in-Progress.
"Addressing distributional shift by declaying planning steps in Dyna-Q algorithm" (with Youxin Wang), Work-in-Progress.
"Universal weight manifolds: Meta learning a shared low-dimensional basis for neural network weights” (with Shuliang Liu, Weilei Feng and Yaping Zhao), Work-in-Progress.