English
Related papers

Related papers: Q-Learning under Finite Model Uncertainty

200 papers

We present a novel $Q$-learning algorithm tailored to solve distributionally robust Markov decision problems where the corresponding ambiguity set of transition probabilities for the underlying Markov decision process is a Wasserstein ball…

Machine Learning · Computer Science 2024-06-21 Ariel Neufeld , Julian Sester

We introduce a general framework for Markov decision problems under model uncertainty in a discrete-time infinite horizon setting. By providing a dynamic programming principle we obtain a local-to-global paradigm, namely solving a local,…

Optimization and Control · Mathematics 2023-01-06 Ariel Neufeld , Julian Sester , Mario Šikić

In this paper, we propose a distributionally robust safety verification method for Markov decision processes where only an ambiguous transition kernel is available instead of the precise transition kernel. We define the ambiguity set around…

Systems and Control · Electrical Eng. & Systems 2024-11-27 Abhijit Mazumdar , Yuting Hou , Rafal Wisniewski

Soft Q-learning is a variation of Q-learning designed to solve entropy regularized Markov decision problems where an agent aims to maximize the entropy regularized value function. Despite its empirical success, there have been limited…

Machine Learning · Computer Science 2024-09-06 Narim Jeong , Donghwan Lee

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

Understanding the theoretical capabilities and limitations of quantum machine learning (QML) models to solve machine learning tasks is crucial to advancing both quantum software and hardware developments. Similarly to the classical setting,…

Quantum Physics · Physics 2026-03-31 Qiuhao Chen , Yuling Jiao , Yinan Li , Xiliang Lu , Jerry Zhijian Yang

The quantum Wasserstein distance (W-distance) is a fundamental metric for quantifying the distinguishability of quantum operations, with critical applications in quantum error correction. However, computing the W-distance remains…

Quantum Physics · Physics 2025-11-18 Changchun Feng , Xinyu Qiu , Laifa Tao , Lin Chen

Neural networks (NNs) are currently changing the computational paradigm on how to combine data with mathematical laws in physics and engineering in a profound way, tackling challenging inverse and ill-posed problems not solvable with…

Machine Learning · Computer Science 2023-02-08 Apostolos F Psaros , Xuhui Meng , Zongren Zou , Ling Guo , George Em Karniadakis

Robustness studies of black-box models is recognized as a necessary task for numerical models based on structural equations and predictive models learned from data. These studies must assess the model's robustness to possible…

Optimization and Control · Mathematics 2022-09-26 Marouane Il Idrissi , Nicolas Bousquet , Fabrice Gamboa , Bertrand Iooss , Jean-Michel Loubes

Process capability indices such as $C_{pk}$ are widely used for manufacturing decisions, yet are typically applied via deterministic thresholding of finite-sample estimates, ignoring uncertainty and leading to unstable outcomes near the…

Applications · Statistics 2026-04-16 Fei Jiang , Lei Yang

Uncertainty quantification (UQ) in deep learning regression is of wide interest, as it supports critical applications including sequential decision making and risk-sensitive tasks. In heteroskedastic regression, where the uncertainty of the…

Machine Learning · Computer Science 2026-03-03 Mikkel Jordahn , Jonas Vestergaard Jensen , James Harrison , Michael Riis Andersen , Mikkel N. Schmidt

Uncertainty Quantification (UQ) is essential in probabilistic machine learning models, particularly for assessing the reliability of predictions. In this paper, we present a systematic framework for estimating both epistemic and aleatoric…

Machine Learning · Statistics 2025-09-11 Marzieh Ajirak , Anand Ravishankar , Petar M. Djuric

Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning…

Machine Learning · Computer Science 2020-03-05 Pan Xu , Quanquan Gu

Machine learning can significantly improve performance for decision-making under uncertainty across a wide range of domains. However, ensuring robustness guarantees requires well-calibrated uncertainty estimates, which can be difficult to…

Machine Learning · Computer Science 2026-02-03 Christopher Yeh , Nicolas Christianson , Alan Wu , Adam Wierman , Yisong Yue

In this paper, for Markov decision processes (MDPs) with unbounded state spaces we present refined upper bounds presented in [Kara et. al. JMLR'23] on finite model approximation errors via optimizing the quantizers used for finite model…

Optimization and Control · Mathematics 2025-10-15 Osman Bicer , Ali D. Kara , Serdar Yuksel

This paper presents a distributionally robust Q-Learning algorithm (DrQ) which leverages Wasserstein ambiguity sets to provide idealistic probabilistic out-of-sample safety guarantees during online learning. First, we follow past work by…

Machine Learning · Computer Science 2021-10-27 Aaron Kandel , Scott J. Moura

In this paper, we propose a data-driven robust safety verification framework for stochastic dynamical systems modeled as Markov decision processes with time-varying and uncertain transition probabilities. Rather than assuming access to the…

Systems and Control · Electrical Eng. & Systems 2025-12-09 Abhijit Mazumdar , Manuela L. Bujorianu , Rafal Wisniewski

Reinforcement learning algorithms often require finiteness of state and action spaces in Markov decision processes (MDPs) (also called controlled Markov chains) and various efforts have been made in the literature towards the applicability…

Machine Learning · Computer Science 2023-09-08 Ali Devran Kara , Naci Saldi , Serdar Yüksel

For infinite-horizon average-cost criterion problems, there exist relatively few rigorous approximation and reinforcement learning results. In this paper, for Markov Decision Processes (MDPs) with standard Borel spaces, (i) we first provide…

Optimization and Control · Mathematics 2024-12-10 Ali Devran Kara , Serdar Yuksel

While neural networks have demonstrated impressive performance across various tasks, accurately quantifying uncertainty in their predictions is essential to ensure their trustworthiness and enable widespread adoption in critical systems.…

Machine Learning · Statistics 2025-11-11 Joseph Wilson , Chris van der Heide , Liam Hodgkinson , Fred Roosta
‹ Prev 1 2 3 10 Next ›