English
Related papers

Related papers: Safe Wasserstein Constrained Deep Q-Learning

200 papers

Distributionally robust optimization (DRO) has emerged as a powerful paradigm for reliable decision-making under uncertainty. This paper focuses on DRO with ambiguity sets defined via the Sinkhorn discrepancy: an entropy-regularized…

Machine Learning · Statistics 2025-12-16 Jie Wang

This paper presents a novel approach to addressing the distributionally robust nonlinear model predictive control (DRNMPC) problem. Current literature primarily focuses on the static Wasserstein distributionally robust optimal control…

Optimization and Control · Mathematics 2023-04-18 Zhengang Zhong , Jia-Jie Zhu

Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved. State-of-the-art approaches to estimate neural uncertainties are often hybrid, combining parametric models with…

Machine Learning · Computer Science 2021-12-03 Joachim Sicking , Maram Akila , Maximilian Pintz , Tim Wirtz , Asja Fischer , Stefan Wrobel

Wasserstein distributionally robust optimization (WDRO) optimizes against worst-case distributional shifts within a specified uncertainty set, leading to enhanced generalization on unseen adversarial examples, compared to standard…

Machine Learning · Computer Science 2025-03-07 Shuang Liu , Yihan Wang , Yifan Zhu , Yibo Miao , Xiao-Shan Gao

In this paper, a risk-aware motion control scheme is considered for mobile robots to avoid randomly moving obstacles when the true probability distribution of uncertainty is unknown. We propose a novel model predictive control (MPC) method…

Robotics · Computer Science 2020-01-15 Astghik Hakobyan , Insoon Yang

We consider exact deterministic mixed-integer programming (MIP) reformulations of distributionally robust chance-constrained programs (DR-CCP) with random right-hand sides over Wasserstein ambiguity sets. The existing MIP formulations are…

Optimization and Control · Mathematics 2020-12-08 Nam Ho-Nguyen , Fatma Kılınç-Karzan , Simge Küçükyavuz , Dabeen Lee

To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) has been proposed to enhance performance across a range of…

Machine Learning · Statistics 2024-09-24 Zhipeng Liang , Xiaoteng Ma , Jose Blanchet , Jiheng Zhang , Zhengyuan Zhou

Reinforcement learning algorithms based on Q-learning are driving Deep Reinforcement Learning (DRL) research towards solving complex problems and achieving super-human performance on many of them. Nevertheless, Q-Learning is known to be…

Machine Learning · Computer Science 2022-06-14 Andrea Cini , Carlo D'Eramo , Jan Peters , Cesare Alippi

Ensuring strict safety guarantees is the paramount challenge for emerging 5G/6G wireless systems, particularly as they increasingly govern mission-critical applications ranging from autonomous UAV swarms to industrial automation. While deep…

Signal Processing · Electrical Eng. & Systems 2026-04-21 Haoran Peng , Tong Wu , Hang Liu , Weijia Zheng , Ying-Jun Angela Zhang , Anna Scaglione

This paper proposes a novel approach to construct data-driven online solutions to optimization problems (P) subject to a class of distributionally uncertain dynamical systems. The introduced framework allows for the simultaneous learning of…

Systems and Control · Electrical Eng. & Systems 2024-07-23 Dan Li , Dariush Fooladivanda , Sonia Martinez

In many real-world applications, ensuring the robustness and stability of deep neural networks (DNNs) is crucial, particularly for image classification tasks that encounter various input perturbations. While data augmentation techniques…

Machine Learning · Statistics 2025-06-26 Jiaming Hu , Debarghya Mukherjee , Ioannis Ch. Paschalidis

We propose a robust Q-learning algorithm for Markov decision processes under model uncertainty when each state-action pair is associated with a finite ambiguity set of candidate transition kernels. This finite-measure framework enables…

Optimization and Control · Mathematics 2026-02-10 Julian Sester , Cécile Decker

Stochastic optimal control usually requires an explicit dynamical model with probability distributions, which are difficult to obtain in practice. In this work, we consider the linear quadratic regulator (LQR) problem of unknown linear…

Optimization and Control · Mathematics 2023-01-18 Feiran Zhao , Keyou You

We propose a novel distributionally robust $Q$-learning algorithm for the non-tabular case accounting for continuous state spaces where the state transition of the underlying Markov decision process is subject to model uncertainty. The…

Machine Learning · Computer Science 2025-05-27 Chung I Lu , Julian Sester , Aijia Zhang

The robustness of Unmanned Surface Vehicles (USV) is crucial when facing unknown and complex marine environments, especially when heteroscedastic observational noise poses significant challenges to sensor-based navigation tasks. Recently,…

Robotics · Computer Science 2025-12-02 Zhaofan Zhang , Minghao Yang , Sihong Xie , Hui Xiong

In recent years, Wasserstein Distributionally Robust Optimization (DRO) has garnered substantial interest for its efficacy in data-driven decision-making under distributional uncertainty. However, limited research has explored the…

Machine Learning · Computer Science 2025-10-01 Ahmad-Reza Ehyaei , Golnoosh Farnadi , Samira Samadi

The Wasserstein distance has emerged as a key metric to quantify distances between probability distributions, with applications in various fields, including machine learning, control theory, decision theory, and biological systems.…

Machine Learning · Computer Science 2026-02-10 Eduardo Figueiredo , Steven Adams , Luca Laurenti

Standard rare-event simulation techniques require exact distributional specifications, which limits their effectiveness in the presence of distributional uncertainty. To address this, we develop a novel framework for estimating rare-event…

Methodology · Statistics 2026-01-06 Dohyun Ahn , Huiyi Chen , Lewen Zheng

Given a set of trajectories demonstrating the execution of a task safely in a constrained MDP with observable rewards but with unknown constraints and non-observable costs, we aim to find a policy that maximizes the likelihood of…

Machine Learning · Computer Science 2026-03-02 George Papadopoulos , George A. Vouros

Markov decision processes (MDPs) are known to be sensitive to parameter specification. Distributionally robust MDPs alleviate this issue by allowing for \emph{ambiguity sets} which give a set of possible distributions over parameter sets.…

Optimization and Control · Mathematics 2021-05-05 Julien Grand-Clément , Christian Kroer