English
Related papers

Related papers: Wasserstein Distributionally Robust Policy Evaluat…

200 papers

A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and…

Machine Learning · Statistics 2020-07-21 John Duchi , Hongseok Namkoong

In strategic scenarios where decision-makers operate at different hierarchical levels, traditional optimization methods are often inadequate for handling uncertainties from incomplete information or unpredictable external factors. To fill…

Systems and Control · Electrical Eng. & Systems 2025-11-10 Jiachen Shen , Jian Shi , Lei Fan , Chenye Wu , Dan Wang , Choong Seon Hong , Zhu Han

We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in practice due to mismatches between training and deployment…

Machine Learning · Computer Science 2025-11-12 Debamita Ghosh , George K. Atia , Yue Wang

This paper introduces Inverse Distributionally Robust Optimization (I-DRO) as a method to infer the conservativeness level of a decision-maker, represented by the size of a Wasserstein metric-based ambiguity set, from the optimal decisions…

Optimization and Control · Mathematics 2024-05-07 Qi Li , Zhirui Liang , Andrey Bernstein , Yury Dvorkin

Reinforcement Learning with Human Feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent. However, existing offline RLHF approaches suffer from overoptimization, where language models degrade by…

Machine Learning · Computer Science 2026-04-20 Sharan Sahu , Martin T. Wells

Policy-based Reinforcement Learning (RL) has established itself as the dominant paradigm in generative recommendation for optimizing sequential user interactions. However, when applied to offline historical logs, these methods suffer a…

Machine Learning · Computer Science 2026-02-12 Jie Jiang , Yusen Huo , Xiangxin Zhan , Changping Wang , Jun Zhang

Distributionally robust policy learning aims to find a policy that performs well under the worst-case distributional shift, and yet most existing methods for robust policy learning consider the worst-case joint distribution of the covariate…

Machine Learning · Computer Science 2025-06-03 Jingyuan Wang , Zhimei Ren , Ruohan Zhan , Zhengyuan Zhou

Distributionally robust optimization (DRO) has been introduced for solving stochastic programs where the distribution of the random parameters is unknown and must be estimated by samples from that distribution. A key element of DRO is the…

Optimization and Control · Mathematics 2019-01-09 Xi Chen , Qihang Lin , Guanglin Xu

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various…

Machine Learning · Computer Science 2025-07-03 Xiaocong Chen , Siyu Wang , Tong Yu , Lina Yao

In this paper, we propose a practical online method for solving a class of distributionally robust optimization (DRO) with non-convex objectives, which has important applications in machine learning for improving the robustness of neural…

Machine Learning · Computer Science 2021-11-15 Qi Qi , Zhishuai Guo , Yi Xu , Rong Jin , Tianbao Yang

This paper extends the Distributionally Robust Optimization (DRO) approach for offline contextual bandits. Specifically, we leverage this framework to introduce a convex reformulation of the Counterfactual Risk Minimization principle.…

Machine Learning · Statistics 2020-11-16 Otmane Sakhi , Louis Faury , Flavian Vasile

Performativity means that the deployment of a predictive model incentivizes agents to strategically adapt their behavior, thereby inducing a model-dependent distribution shift. Practitioners often repeatedly retrain the model on data…

Optimization and Control · Mathematics 2026-02-09 Siyi Wang , Zifan Wang , Karl H. Johansson

This work presents a new Distributionally Robust Optimization approach, using $p$-Wasserstein metrics, to analyze a stochastic program in a general context. The ambiguity set in this approach depends on the decision variable and is…

Optimization and Control · Mathematics 2023-03-08 Diego Fonseca , Mauricio Junca

Recently, there has been a growing interest in distributionally robust optimization (DRO) as a principled approach to data-driven decision making. In this paper, we consider a distributionally robust two-stage stochastic optimization…

Optimization and Control · Mathematics 2020-12-07 Zhe Zhang , Shabbir Ahmed , Guanghui Lan

Route planning is essential to mobile robot navigation problems. In recent years, deep reinforcement learning (DRL) has been applied to learning optimal planning policies in stochastic environments without prior knowledge. However, existing…

Robotics · Computer Science 2023-04-21 Xi Lin , Paul Szenher , John D. Martin , Brendan Englot

Intensively studied in theory as a promising data-driven tool for decision-making under ambiguity, two-stage distributionally robust optimization (DRO) problems over Wasserstein balls are not necessarily easy to solve in practice. This is…

Optimization and Control · Mathematics 2023-01-03 Youngchae Cho , Insoon Yang

Differential dynamic programming (DDP) is a popular technique for solving nonlinear optimal control problems with locally quadratic approximations. However, existing DDP methods are not designed for stochastic systems with unknown…

Systems and Control · Electrical Eng. & Systems 2023-05-18 Astghik Hakobyan , Insoon Yang

Distributionally robust optimization (DRO) has attracted attention in machine learning due to its connections to regularization, generalization, and robustness. Existing work has considered uncertainty sets based on phi-divergences and…

Machine Learning · Computer Science 2019-05-28 Matthew Staib , Stefanie Jegelka

Real-world deployments routinely face distribution shifts, group imbalances, and adversarial perturbations, under which the traditional Empirical Risk Minimization (ERM) framework can degrade severely. Distributionally Robust Optimization…

Machine Learning · Computer Science 2026-02-19 Difei Xu , Meng Ding , Zebin Ma , Huanyi Xie , Youming Tao , Aicha Slaitane , Di Wang

We describe a new approach for managing aleatoric uncertainty in the Reinforcement Learning (RL) paradigm. Instead of selecting actions according to a single statistic, we propose a distributional method based on the second-order stochastic…

Machine Learning · Computer Science 2020-10-08 John D. Martin , Michal Lyskawinski , Xiaohu Li , Brendan Englot