English
Related papers

Related papers: Reinforcement learning based data assimilation for…

200 papers

In this paper, we present an online reinforcement learning algorithm for constrained Markov decision processes with a safety constraint. Despite the necessary attention of the scientific community, considering stochastic stopping time, the…

Machine Learning · Computer Science 2024-03-26 Abhijit Mazumdar , Rafal Wisniewski , Manuela L. Bujorianu

Modern data-driven surrogate models for weather forecasting provide accurate short-term predictions but inaccurate and nonphysical long-term forecasts. This paper investigates online weather prediction using machine learning surrogates…

Signal Processing · Electrical Eng. & Systems 2025-02-12 Melissa Adrian , Daniel Sanz-Alonso , Rebecca Willett

Learning data representations under uncertainty is an important task that emerges in numerous scientific computing and data analysis applications. However, uncertainty quantification techniques are computationally intensive and become…

Machine Learning · Computer Science 2025-08-06 Paz Fink Shustin , Shashanka Ubaru , Małgorzata J. Zimoń , Songtao Lu , Vasileios Kalantzis , Lior Horesh , Haim Avron

We are interested in learning models of non-stationary environments, which can be framed as a multi-task learning problem. Model-free reinforcement learning algorithms can achieve good asymptotic performance in multi-task learning at a cost…

Machine Learning · Computer Science 2020-11-24 Elahe Aghapour , Nora Ayanian

Machine learning employs dynamical algorithms that mimic the human capacity to learn, where the reinforcement learning ones are among the most similar to humans in this respect. On the other hand, adaptability is an essential aspect to…

Quantum Physics · Physics 2018-10-15 F. Albarrán-Arriagada , J. C. Retamal , E. Solano , L. Lamata

Model-free deep reinforcement learning (RL) agents can learn an effective policy directly from repeated interactions with a black-box environment. However in practice, the algorithms often require large amounts of training experience to…

Machine Learning · Computer Science 2020-05-29 Parth Chadha

We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing $\alpha$-divergences,…

Machine Learning · Statistics 2017-03-09 Stefan Depeweg , José Miguel Hernández-Lobato , Finale Doshi-Velez , Steffen Udluft

Data assimilation is an iterative approach to the problem of estimating the state of a dynamical system using both current and past observations of the system together with a model for the system's time evolution. Rather than solving the…

Data Analysis, Statistics and Probability · Physics 2007-05-23 Brian R. Hunt , Eric J. Kostelich , Istvan Szunyogh

In complex large-scale systems such as climate, important effects are caused by a combination of confounding processes that are not fully observable. The identification of sources from observations of system state is vital for attribution…

Machine Learning · Statistics 2023-03-22 Joseph Hart , Mamikon Gulian , Indu Manickam , Laura Swiler

Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be…

Computer Vision and Pattern Recognition · Computer Science 2017-10-31 Toan Tran , Trung Pham , Gustavo Carneiro , Lyle Palmer , Ian Reid

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP).…

Machine Learning · Computer Science 2022-02-01 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

Data assimilation (DA) is widely used to combine physical knowledge and observations. It is nowadays commonly used in geosciences to perform parametric calibration. In a context of climate change, old calibrations can not necessarily be…

Machine Learning · Statistics 2021-06-23 Rem-Sophia Mouradi , Cédric Goeury , Olivier Thual , Fabrice Zaoui , Pablo Tassi

This paper presents a novel methodology for tractably solving optimal control and offline reinforcement learning problems for high-dimensional systems. This work is motivated by the ongoing challenges of safety, computation, and optimality…

Optimization and Control · Mathematics 2022-07-06 Aaron Kandel , Saehong Park , Scott Moura

Bayesian policy reuse (BPR) is a general policy transfer framework for selecting a source policy from an offline library by inferring the task belief based on some observation signals and a trained observation model. In this paper, we…

Machine Learning · Computer Science 2023-07-14 Jinmei Liu , Zhi Wang , Chunlin Chen , Daoyi Dong

Reinforcement Learning (RL) based methods have seen their paramount successes in solving serial decision-making and control problems in recent years. For conventional RL formulations, Markov Decision Process (MDP) and state-action-value…

Machine Learning · Computer Science 2020-06-09 Ziyao Zhang , Liang Ma , Kin K. Leung , Konstantinos Poularakis , Mudhakar Srivatsa

In the standard data analysis framework, data is collected (once and for all), and then data analysis is carried out. However, with the advancement of digital technology, decision-makers constantly analyze past data and generate new data…

Machine Learning · Statistics 2024-12-25 Jin Li , Ye Luo , Zigan Wang , Xiaowei Zhang

Identifying uncertainty and taking mitigating actions is crucial for safe and trustworthy reinforcement learning agents, especially when deployed in high-risk environments. In this paper, risk sensitivity is promoted in a model-based…

Machine Learning · Computer Science 2021-11-10 Stefan Radic Webster , Peter Flach

We review the field of data assimilation (DA) from a Bayesian perspective and show that, in addition to its by now common application to state estimation, DA may be used for model selection. An important special case of the latter is the…

Applications · Statistics 2017-04-05 Alberto Carrassi , Marc Bocquet , Alexis Hannart , Michael Ghil

Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on…

All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient…

Machine Learning · Computer Science 2018-04-05 Trevor Barron , Oliver Obst , Heni Ben Amor