English
Related papers

Related papers: Uncertainty Prioritized Experience Replay

200 papers

Equation learning aims to infer differential equation models from data. While a number of studies have shown that differential equation models can be successfully identified when the data are sufficiently detailed and corrupted with…

Quantitative Methods · Quantitative Biology 2021-09-30 Simon Martina-Perez , Matthew J. Simpson , Ruth E. Baker

Quantifying the uncertainty of supervised learning models plays an important role in making more reliable predictions. Epistemic uncertainty, which usually is due to insufficient knowledge about the model, can be reduced by collecting more…

Machine Learning · Computer Science 2022-01-27 Xinlei Zhou , Han Liu , Farhad Pourpanah , Tieyong Zeng , Xizhao Wang

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

State-of-the-art deep Q-learning methods update Q-values using state transition tuples sampled from the experience replay buffer. This strategy often uniformly and randomly samples or prioritizes data sampling based on measures such as the…

Machine Learning · Computer Science 2023-06-28 Zhang-Wei Hong , Tao Chen , Yen-Chen Lin , Joni Pajarinen , Pulkit Agrawal

In reinforcement learning, we typically refer to unsupervised pre-training when we aim to pre-train a policy without a priori access to the task specification, i.e. rewards, to be later employed for efficient learning of downstream tasks.…

Machine Learning · Computer Science 2025-10-21 Riccardo Zamboni , Mirco Mutti , Marcello Restelli

We introduce DreamerV3-XP, an extension of DreamerV3 that improves exploration and learning efficiency. This includes (i) a prioritized replay buffer, scoring trajectories by return, reconstruction loss, and value error and (ii) an…

Machine Learning · Computer Science 2025-10-27 Lukas Bierling , Davide Pasero , Jan-Henrik Bertrand , Kiki Van Gerwen

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the…

Machine Learning · Computer Science 2018-09-10 Sameera Lanka , Tianfu Wu

Poor sample efficiency is a major limitation of deep reinforcement learning in many domains. This work presents an attention-based method to project neural network inputs into an efficient representation space that is invariant under…

Machine Learning · Computer Science 2020-03-23 John Mern , Dorsa Sadigh , Mykel J. Kochenderfer

Effective quantification of uncertainty is an essential and still missing step towards a greater adoption of deep-learning approaches in different applications, including mission-critical ones. In particular, investigations on the…

Machine Learning · Computer Science 2023-04-14 Marco Forgione , Dario Piga

We propose a novel iterative algorithm for estimating a deterministic but unknown parameter vector in the presence of model uncertainties. This iterative algorithm is based on a system model where an overall noise term describes both, the…

Statistics Theory · Mathematics 2017-11-27 Oliver Lang , Michael Lunglmayr , Mario Huemer

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Antonio Loquercio , Mattia Segù , Davide Scaramuzza

Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are merely punctuated…

Machine Learning · Computer Science 2023-08-22 Akash Velu , Skanda Vaidyanath , Dilip Arumugam

Clinical decision requires reasoning in the presence of imperfect data. DTs are a well-known decision support tool, owing to their interpretability, fundamental in safety-critical contexts such as medical diagnosis. However, learning DTs…

Due to the difficulty of acquiring large-scale explicit user feedback, implicit feedback (e.g., clicks or other interactions) is widely applied as an alternative source of data, where user-item interactions can be modeled as a bipartite…

Information Retrieval · Computer Science 2024-11-15 Xinyu He , Jose Sepulveda , Mostafa Rahmani , Alyssa Woo , Fei Wang , Hanghang Tong

Transformers are designed for discrete tokens, yet many real-world signals are continuous processes observed through noisy sampling. Discrete tokenizations (raw values, patches, finite differences) can be brittle in low signal-to-noise…

Machine Learning · Computer Science 2026-01-21 Griffin Kearney

Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose…

The calibration of predictive distributions has been widely studied in deep learning, but the same cannot be said about the more specific epistemic uncertainty as produced by Deep Ensembles, Bayesian Deep Networks, or Evidential Deep…

Machine Learning · Computer Science 2024-07-18 Mohammed Fellaji , Frédéric Pennerath , Brieuc Conan-Guez , Miguel Couceiro

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

Retrieval augmented Question Answering (QA) helps QA models overcome knowledge gaps by incorporating retrieved evidence, typically a set of passages, alongside the question at test time. Previous studies show that this approach improves QA…

Computation and Language · Computer Science 2025-09-12 Laura Perez-Beltrachini , Mirella Lapata

We study continual learning in the large scale setting where tasks in the input sequence are not limited to classification, and the outputs can be of high dimension. Among multiple state-of-the-art methods, we found vanilla experience…

Machine Learning · Computer Science 2020-10-07 Yogesh Balaji , Mehrdad Farajtabar , Dong Yin , Alex Mott , Ang Li
‹ Prev 1 8 9 10 Next ›