English
Related papers

Related papers: Sample Efficient Deep Reinforcement Learning via U…

200 papers

In statistical dialogue management, the dialogue manager learns a policy that maps a belief state to an action for the system to perform. Efficient exploration is key to successful policy optimisation. Current deep reinforcement learning…

Machine Learning · Statistics 2017-12-04 Christopher Tegho , Paweł Budzianowski , Milica Gašić

Ensemble models are powerful model building tools that are developed with a focus to improve the accuracy of model predictions. They find applications in time series forecasting in varied scenarios including but not limited to process…

We propose a method for variable selection in the intensity function of spatial point processes that combines sparsity-promoting estimation with noise-robust model selection. As high-resolution spatial data becomes increasingly available…

Methodology · Statistics 2025-10-30 Dominik Sturm , Ivo F. Sbalzarini

Bayesian neural networks with latent variables are scalable and flexible probabilistic models: They account for uncertainty in the estimation of the network weights and, by making use of latent variables, can capture complex noise patterns…

Machine Learning · Statistics 2018-06-19 Stefan Depeweg , José Miguel Hernández-Lobato , Finale Doshi-Velez , Steffen Udluft

In this paper, we revisit techniques for uncertainty estimation within deep neural networks and consolidate a suite of techniques to enhance their reliability. Our investigation reveals that an integrated application of diverse…

Computer Vision and Pattern Recognition · Computer Science 2024-03-04 Yuting Li , Yingyi Chen , Xuanlong Yu , Dexiong Chen , Xi Shen

Datasets in engineering applications are often limited and contaminated, mainly due to unavoidable measurement noise and signal distortion. Thus, using conventional data-driven approaches to build a reliable discriminative model, and…

Machine Learning · Statistics 2020-04-14 Xihaier Luo , Ahsan Kareem

Robust reinforcement learning (RRL) aims at seeking a robust policy to optimize the worst case performance over an uncertainty set of Markov decision processes (MDPs). This set contains some perturbed MDPs from a nominal MDP (N-MDP) that…

Machine Learning · Computer Science 2023-11-21 Ukjo Hwang , Songnam Hong

Deep Ensembles, as a type of Bayesian Neural Networks, can be used to estimate uncertainty on the prediction of multiple neural networks by collecting votes from each network and computing the difference in those predictions. In this paper,…

Machine Learning · Computer Science 2023-07-10 Illia Oleksiienko , Alexandros Iosifidis

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…

Machine Learning · Computer Science 2021-10-28 Mete Kemertas , Tristan Aumentado-Armstrong

Imaging is a standard example of an inverse problem, where the task of reconstructing a ground truth from a noisy measurement is ill-posed. Recent state-of-the-art approaches for imaging use deep learning, spearheaded by unrolled and…

Image reconstruction methods based on deep neural networks have shown outstanding performance, equalling or exceeding the state-of-the-art results of conventional approaches, but often do not provide uncertainty information about the…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Riccardo Barbano , Željko Kereta , Chen Zhang , Andreas Hauptmann , Simon Arridge , Bangti Jin

Reinforcement learning (RL) can be used to create a tactical decision-making agent for autonomous driving. However, previous approaches only output decisions and do not provide information about the agent's confidence in the recommended…

Robotics · Computer Science 2020-11-04 Carl-Johan Hoel , Krister Wolff , Leo Laine

Deep neural networks are in the limelight of machine learning with their excellent performance in many data-driven applications. However, they can lead to inaccurate predictions when queried in out-of-distribution data points, which can…

Machine Learning · Computer Science 2023-03-01 Yana Stoyanova , Soroush Ghandi , Maryam Tavakol

Data imbalance is ubiquitous when applying machine learning to real-world problems, particularly regression problems. If training data are imbalanced, the learning is dominated by the densely covered regions of the target distribution and…

Machine Learning · Computer Science 2024-10-29 Yuchang Jiang , Vivien Sainte Fare Garnot , Konrad Schindler , Jan Dirk Wegner

Reinforcement Learning has applications in field of mechatronics, robotics, and other resource-constrained control system. Problem of resource allocation is primarily solved using traditional predefined techniques and modern deep learning…

Machine Learning · Computer Science 2021-06-18 Neel Gandhi , Shakti Mishra

Uncertainty sampling in active learning is heavily used in practice to reduce the annotation cost. However, there has been no wide consensus on the function to be used for uncertainty estimation in binary classification tasks and…

Machine Learning · Computer Science 2021-11-01 Anant Raj , Francis Bach

While Deep Neural Networks (DNNs) achieve state-of-the-art accuracy in various applications, they often fall short in accurately estimating their predictive uncertainty and, in turn, fail to recognize when these predictions may be wrong.…

Machine Learning · Computer Science 2020-07-22 Ankur Mallick , Chaitanya Dwivedi , Bhavya Kailkhura , Gauri Joshi , T. Yong-Jin Han

In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on…

Machine Learning · Computer Science 2020-12-22 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean…

Machine Learning · Statistics 2022-07-13 Yingsong Huang , Bing Bai , Shengwei Zhao , Kun Bai , Fei Wang

Model uncertainty quantification involves measuring and evaluating the uncertainty linked to a model's predictions, helping assess their reliability and confidence. Noise injection is a technique used to enhance the robustness of neural…

Machine Learning · Statistics 2025-04-25 Xueqiong Yuan , Jipeng Li , Ercan Engin Kuruoglu