English
Related papers

Related papers: Estimating Risk and Uncertainty in Deep Reinforcem…

200 papers

Bringing deep neural networks (DNNs) into safety critical applications such as automated driving, medical imaging and finance, requires a thorough treatment of the model's uncertainties. Training deep neural networks is already resource…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Julian Burghoff , Robin Chan , Hanno Gottschalk , Annika Muetze , Tobias Riedlinger , Matthias Rottmann , Marius Schubert

This paper studies directed exploration for reinforcement learning agents by tracking uncertainty about the value of each available action. We identify two sources of uncertainty that are relevant for exploration. The first originates from…

Machine Learning · Computer Science 2017-11-30 Thomas M. Moerland , Joost Broekens , Catholijn M. Jonker

Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging…

Machine Learning · Computer Science 2025-07-18 Chenrui Zhu , Louenas Bounia , Vu Linh Nguyen , Sébastien Destercke , Arthur Hoarau

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

Various strategies for active learning have been proposed in the machine learning literature. In uncertainty sampling, which is among the most popular approaches, the active learner sequentially queries the label of those instances for…

Machine Learning · Computer Science 2019-09-04 Vu-Linh Nguyen , Sébastien Destercke , Eyke Hüllermeier

Deep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour…

Machine Learning · Computer Science 2022-10-10 Adrian Ly , Richard Dazeley , Peter Vamplew , Francisco Cruz , Sunil Aryal

Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we…

Machine Learning · Computer Science 2022-04-21 Matias Valdenegro-Toro , Daniel Saromo

Data-driven control in unknown environments requires a clear understanding of the involved uncertainties for ensuring safety and efficient exploration. While aleatoric uncertainty that arises from measurement noise can often be explicitly…

Machine Learning · Computer Science 2023-07-13 Neha Das , Jonas Umlauft , Armin Lederer , Thomas Beckers , Sandra Hirche

We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification. In this context, all known methods are based on extracting uncertainty signals from a trained network optimized to solve the…

Machine Learning · Computer Science 2019-04-25 Yonatan Geifman , Guy Uziel , Ran El-Yaniv

We provide single-model estimates of aleatoric and epistemic uncertainty for deep neural networks. To estimate aleatoric uncertainty, we propose Simultaneous Quantile Regression (SQR), a loss function to learn all the conditional quantiles…

Machine Learning · Statistics 2019-09-09 Natasa Tagasovska , David Lopez-Paz

Autonomous and semi-autonomous systems are using deep learning models to improve decision-making. However, deep classifiers can be overly confident in their incorrect predictions, a major issue especially in safety-critical domains. The…

Machine Learning · Computer Science 2024-12-05 Murat Sensoy , Lance M. Kaplan , Simon Julier , Maryam Saleki , Federico Cerutti

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Machine Learning · Computer Science 2026-04-30 Disha Singha

We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and…

Machine Learning · Computer Science 2023-09-12 Marin Vlastelica , Sebastian Blaes , Cristina Pineri , Georg Martius

Identifying and disentangling sources of predictive uncertainty is essential for trustworthy supervised learning. We argue that widely used second-order methods that disentangle aleatoric and epistemic uncertainty are fundamentally…

Machine Learning · Computer Science 2026-02-09 Sebastián Jiménez , Mira Jürgens , Willem Waegeman

We develop a framework for interacting with uncertain environments in reinforcement learning (RL) by leveraging preferences in the form of utility functions. We claim that there is value in considering different risk measures during…

Machine Learning · Computer Science 2021-02-23 Hannes Eriksson , Christos Dimitrakakis

While many algorithmic extensions to Deep Q-Networks (DQN) have been proposed, there remains limited understanding of how different improvements interact. In particular, multi-step and ensemble style extensions have shown promise in…

Machine Learning · Computer Science 2025-06-09 Adrian Ly , Richard Dazeley , Peter Vamplew , Francisco Cruz , Sunil Aryal

Deep Reinforcement Learning (RL) has considerably advanced over the past decade. At the same time, state-of-the-art RL algorithms require a large computational budget in terms of training time to converge. Recent work has started to…

Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inaccurate and impose a…

Machine Learning · Computer Science 2019-06-21 Ali Malik , Volodymyr Kuleshov , Jiaming Song , Danny Nemer , Harlan Seymour , Stefano Ermon

Instability and variability of Deep Reinforcement Learning (DRL) algorithms tend to adversely affect their performance. Averaged-DQN is a simple extension to the DQN algorithm, based on averaging previously learned Q-values estimates, which…

Artificial Intelligence · Computer Science 2017-03-13 Oron Anschel , Nir Baram , Nahum Shimkin

Uncertainty representation and quantification are paramount in machine learning and constitute an important prerequisite for safety-critical applications. In this paper, we propose novel measures for the quantification of aleatoric and…

Machine Learning · Computer Science 2024-04-22 Paul Hofman , Yusuf Sale , Eyke Hüllermeier