English
Related papers

Related papers: Reinforcement learning based data assimilation for…

200 papers

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of…

Machine Learning · Computer Science 2023-11-02 Udaya Ghai , Arushi Gupta , Wenhan Xia , Karan Singh , Elad Hazan

A fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way of an abstract state…

Machine Learning · Computer Science 2024-03-18 Cameron Allen , Neev Parikh , Omer Gottesman , George Konidaris

Autonomous robots operating in complex, unstructured environments face significant challenges due to latent, unobserved factors that obscure their understanding of both their internal state and the external world. Addressing this challenge…

Robotics · Computer Science 2026-04-02 Alejandro Murillo-Gonzalez , Lantao Liu

Reinforcement learning algorithms are typically designed for generic Markov Decision Processes (MDPs), where any state-action pair can lead to an arbitrary transition distribution. In many practical systems, however, only a subset of the…

Machine Learning · Computer Science 2026-03-05 Davide Maran , Davide Salaorni , Marcello Restelli

Reinforcement learning methods are increasingly used to optimise dialogue policies from experience. Most current techniques are model-free: they directly estimate the utility of various actions, without explicit model of the interaction…

Artificial Intelligence · Computer Science 2013-04-09 Pierre Lison

Conventional recursive filtering approaches, designed for quantifying the state of an evolving uncertain dynamical system with intermittent observations, use a sequence of (i) an uncertainty propagation step followed by (ii) a step where…

Probability · Mathematics 2015-06-18 Wonjung Lee , Chris Farmer

Starting from limited measurements of a turbulent flow, data assimilation (DA) attempts to estimate all the spatio-temporal scales of motion. Success is dependent on whether the system is observable from the measurements, or how much of the…

Fluid Dynamics · Physics 2026-02-16 Andrew Cleary , Qi Wang , Tamer A. Zaki

This work presents a data-driven method for learning low-dimensional time-dependent physics-based surrogate models whose predictions are endowed with uncertainty estimates. We use the operator inference approach to model reduction that…

Numerical Analysis · Mathematics 2025-03-19 Shane A. McQuarrie , Anirban Chaudhuri , Karen E. Willcox , Mengwu Guo

In this contribution we present an accelerated optimization-based approach for combined state and parameter reduction of a parametrized linear control system which is then used as a surrogate model in a Bayesian inverse setting. Following…

Optimization and Control · Mathematics 2016-08-22 Christian Himpe , Mario Ohlberger

For applications in healthcare, physics, energy, robotics, and many other fields, designing maximally informative experiments is valuable, particularly when experiments are expensive, time-consuming, or pose safety hazards. While existing…

Machine Learning · Computer Science 2022-03-09 Vincent Lim , Ellen Novoseller , Jeffrey Ichnowski , Huang Huang , Ken Goldberg

Many real-world systems are modelled using complex ordinary differential equations (ODEs). However, the dimensionality of these systems can make them challenging to analyze. Dimensionality reduction techniques like Proper Orthogonal…

Computational Engineering, Finance, and Science · Computer Science 2025-02-26 Abhishek Ajayakumar , Soumyendu Raha

We study how a Reinforcement Learning (RL) system can remain sample-efficient when learning from an imperfect model of the environment. This is particularly challenging when the learning system is resource-constrained and in continual…

Machine Learning · Computer Science 2024-07-01 Bradley Burega , John D. Martin , Luke Kapeluck , Michael Bowling

Data assimilation algorithms estimate the state of a dynamical system from partial observations, where the successful performance of these algorithms hinges on costly parameter tuning and on employing an accurate model for the dynamics.…

Machine Learning · Statistics 2026-03-24 Melissa Adrian , Daniel Sanz-Alonso , Rebecca Willett

Surrogate modeling is of great practical significance for parametric differential equation systems. In contrast to classical numerical methods, using physics-informed deep learning methods to construct simulators for such systems is a…

Numerical Analysis · Mathematics 2025-01-03 Xili Wang , Kejun Tang , Jiayu Zhai , Xiaoliang Wan , Chao Yang

Data assimilation, consisting in the combination of a dynamical model with a set of noisy and incomplete observations in order to infer the state of a system over time, involves uncertainty in most settings. Building upon an existing…

Machine Learning · Computer Science 2026-03-02 Anthony Frion , David S Greenberg

In real-world reinforcement learning applications the learner's observation space is ubiquitously high-dimensional with both relevant and irrelevant information about the task at hand. Learning from high-dimensional observations has been…

Machine Learning · Computer Science 2022-06-10 Yonathan Efroni , Dylan J. Foster , Dipendra Misra , Akshay Krishnamurthy , John Langford

Data assimilation (DA) provides a general framework for estimation in dynamical systems based on the concepts of Bayesian inference. This constitutes a common basis for the different linear and nonlinear filtering and smoothing techniques…

Optimization and Control · Mathematics 2023-03-08 Tarek Diaa-Eldeen , Marcus Krogh Nielsen , Carl Fredrik Berg , Morten Hovd , John Bagterp Jørgensen

We consider a class of stochastic programming problems where the implicitly decision-dependent random variable follows a nonparametric regression model with heteroscedastic error. The Clarke subdifferential and surrogate functions are not…

Optimization and Control · Mathematics 2025-05-13 Boyang Shen , Junyi Liu

Model-based reinforcement learning could enable sample-efficient learning by quickly acquiring rich knowledge about the world and using it to improve behaviour without additional data. Learned dynamics models can be directly used for…

Machine Learning · Computer Science 2019-10-15 Rinu Boney , Juho Kannala , Alexander Ilin

Autonomous robots require high degrees of cognitive and motoric intelligence to come into our everyday life. In non-structured environments and in the presence of uncertainties, such degrees of intelligence are not easy to obtain.…