English
Related papers

Related papers: Bootstrap Advantage Estimation for Policy Optimiza…

200 papers

Off-policy evaluation (OPE) methods aim to estimate the value of a new reinforcement learning (RL) policy prior to deployment. Recent advances have shown that leveraging auxiliary datasets, such as those synthesized by generative models,…

Machine Learning · Computer Science 2025-07-29 Aishwarya Mandyam , Jason Meng , Ge Gao , Jiankai Sun , Mac Schwager , Barbara E. Engelhardt , Emma Brunskill

In this paper we present a technique for using the bootstrap to estimate the operating characteristics and their variability for certain types of ensemble methods. Bootstrapping a model can require a huge amount of work if the training data…

Machine Learning · Statistics 2017-10-26 Anthony Gamst , Jay-Calvin Reyes , Alden Walker

Hyperparameter optimization (HPO) is generally treated as a bi-level optimization problem that involves fitting a (probabilistic) surrogate model to a set of observed hyperparameter responses, e.g. validation loss, and consequently…

Machine Learning · Computer Science 2021-10-18 Hadi S. Jomaa , Jonas Falkner , Lars Schmidt-Thieme

Although the many efforts to apply deep reinforcement learning to query optimization in recent years, there remains room for improvement as query optimizers are complex entities that require hand-designed tuning of workloads and datasets.…

Databases · Computer Science 2023-06-05 Yuri Kim , Yewon Choi , Yujung Gil , Sanghee Lee , Heesik Shin , Jaehyok Chong

Overestimation bias control techniques are used by the majority of high-performing off-policy reinforcement learning algorithms. However, most of these techniques rely on pre-defined bias correction policies that are either not flexible…

Machine Learning · Computer Science 2022-02-01 Arsenii Kuznetsov , Alexander Grishin , Artem Tsypin , Arsenii Ashukha , Artur Kadurin , Dmitry Vetrov

In addition to their undisputed success in solving classical optimization problems, neuroevolutionary and population-based algorithms have become an alternative to standard reinforcement learning methods. However, evolutionary methods often…

Neural and Evolutionary Computing · Computer Science 2021-05-18 Jörg Stork , Martin Zaefferer , Nils Eisler , Patrick Tichelmann , Thomas Bartz-Beielstein , A. E. Eiben

The data scarcity problem in emotion recognition from electroencephalography (EEG) leads to difficulty in building an affective model with high accuracy using machine learning algorithms or deep neural networks. Inspired by emerging deep…

Signal Processing · Electrical Eng. & Systems 2020-06-18 Yun Luo , Li-Zhen Zhu , Zi-Yu Wan , Bao-Liang Lu

We propose the first boosting algorithm for off-policy learning from logged bandit feedback. Unlike existing boosting methods for supervised learning, our algorithm directly optimizes an estimate of the policy's expected reward. We analyze…

Machine Learning · Computer Science 2023-05-03 Ben London , Levi Lu , Ted Sandler , Thorsten Joachims

Reinforcement learning has been shown to perform a range of complex tasks through interaction with an environment or collected leveraging experience. However, many of these approaches presume optimal or near optimal experiences or the…

Machine Learning · Computer Science 2021-09-21 Chapman Siu , Jason Traish , Richard Yi Da Xu

Variational autoencoder (VAE) is a deep generative model for unsupervised learning, allowing to encode observations into the meaningful latent space. VAE is prone to catastrophic forgetting when tasks arrive sequentially, and only the data…

Machine Learning · Computer Science 2021-11-04 Anna Kuzina , Evgenii Egorov , Evgeny Burnaev

Accurate statistical inference in logistic regression models remains a critical challenge when the ratio between the number of parameters and sample size is not negligible. This is because approximations based on either classical asymptotic…

Methodology · Statistics 2022-08-19 Qian Zhao , Emmanuel J. Candes

Our goal is to deploy a high-accuracy system starting with zero training examples. We consider an "on-the-job" setting, where as inputs arrive, we use real-time crowdsourcing to resolve uncertainty where needed and output our prediction…

Artificial Intelligence · Computer Science 2015-12-09 Keenon Werling , Arun Chaganty , Percy Liang , Chris Manning

This paper investigates bootstrap-based bias correction of semiparametric estimators of the long memory parameter, $d$, in fractionally integrated processes. The re-sampling method involves the application of the sieve bootstrap to data…

Methodology · Statistics 2016-03-08 Don S. Poskitt , Gael M. Martin , Simone D. Grose

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

Machine Learning · Computer Science 2019-03-04 Michael Kuchnik , Virginia Smith

Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…

Machine Learning · Statistics 2025-01-16 Shulei Wang

Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in…

Machine Learning · Computer Science 2022-12-07 Changming Zhao , Dongrui Wu , Jian Huang , Ye Yuan , Hai-Tao Zhang , Ruimin Peng , Zhenhua Shi

This paper investigates the accuracy of bootstrap-based inference in the case of long memory fractionally integrated processes. The re-sampling method is based on the semi-parametric sieve approach, whereby the dynamics in the process used…

Methodology · Statistics 2016-03-08 D. S. Poskitt , Simone D. Grose , Gael M. Martin

In reinforcement learning (RL), state representations are key to dealing with large or continuous state spaces. While one of the promises of deep learning algorithms is to automatically construct features well-tuned for the task they try to…

Machine Learning · Computer Science 2023-06-21 Charline Le Lan , Stephen Tu , Mark Rowland , Anna Harutyunyan , Rishabh Agarwal , Marc G. Bellemare , Will Dabney

Optimistic value estimates provide one mechanism for directed exploration in reinforcement learning (RL). The agent acts greedily with respect to an estimate of the value plus what can be seen as a value bonus. The value bonus can be…

Machine Learning · Computer Science 2026-02-16 Abdul Wahab , Raksha Kumaraswamy , Martha White

In recent years, there has been significant progress in applying deep reinforcement learning (RL) for solving challenging problems across a wide variety of domains. Nevertheless, convergence of various methods has been shown to suffer from…

Machine Learning · Computer Science 2022-08-19 Pranav Khanna , Guy Tennenholtz , Nadav Merlis , Shie Mannor , Chen Tessler