English
Related papers

Related papers: Importance Resampling for Off-policy Prediction

200 papers

Learning in a lifelong setting, where the dynamics continually evolve, is a hard challenge for current reinforcement learning algorithms. Yet this would be a much needed feature for practical applications. In this paper, we propose an…

Machine Learning · Computer Science 2021-12-14 Pierre Liotet , Francesco Vidaich , Alberto Maria Metelli , Marcello Restelli

Importance Sampling methods are broadly used to approximate posterior distributions or some of their moments. In its standard approach, samples are drawn from a single proposal distribution and weighted properly. However, since the…

Computation · Statistics 2019-11-05 Víctor Elvira , Luca Martino , David Luengo , Mónica F. Bugallo

Understanding systems by forward and inverse modeling is a recurrent topic of research in many domains of science and engineering. In this context, Monte Carlo methods have been widely used as powerful tools for numerical inference and…

Computation · Statistics 2022-02-14 F. Llorente , L. Martino , D. Delgado , G. Camps-Valls

The widespread adoption of large language models (LLMs) across industries has increased the demand for high-quality and customizable outputs. However, traditional alignment methods often require retraining large pretrained models, making it…

Computation and Language · Computer Science 2025-12-16 Yi Liu , Dianqing Liu , Mingye Zhu , Junbo Guo , Yongdong Zhang , Zhendong Mao

Experience replay is a key component in reinforcement learning for stabilizing learning and improving sample efficiency. Its typical implementation samples transitions with replacement from a replay buffer. In contrast, in supervised…

Machine Learning · Computer Science 2025-12-05 Yasuhiro Fujita

Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…

Machine Learning · Computer Science 2021-02-24 Brett Daley , Cameron Hickert , Christopher Amato

Developing accurate off-policy estimators is crucial for both evaluating and optimizing for new policies. The main challenge in off-policy estimation is the distribution shift between the logging policy that generates data and the target…

Machine Learning · Computer Science 2023-10-25 Noveen Sachdeva , Lequn Wang , Dawen Liang , Nathan Kallus , Julian McAuley

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Machine Learning · Computer Science 2025-09-22 Shiwan Zhao , Xuyang Zhao , Jiaming Zhou , Aobo Kong , Qicheng Li , Yong Qin

Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform replay improves over this strong baseline. Across diverse RL settings, we show that the…

Machine Learning · Computer Science 2026-05-19 Michal Korniak , Mikołaj Czarnecki , Yarden As , Piotr Miłoś , Pieter Abbeel , Michal Nauman

Variational Inference (VI) is a popular alternative to asymptotically exact sampling in Bayesian inference. Its main workhorse is optimization over a reverse Kullback-Leibler divergence (RKL), which typically underestimates the tail of the…

Machine Learning · Statistics 2021-07-01 Ghassen Jerfel , Serena Wang , Clara Fannjiang , Katherine A. Heller , Yian Ma , Michael I. Jordan

This Note investigates the bias of the sampling importance resampling (SIR) filter in estimation of the state transition noise in the state space model. The SIR filter may suffer from sample impoverishment that is caused by the resampling…

Systems and Control · Computer Science 2017-07-31 Tiancheng Li

For reinforcement learning on complex stochastic systems where many factors dynamically impact the output trajectories, it is desirable to effectively leverage the information from historical samples collected in previous iterations to…

Machine Learning · Statistics 2022-09-13 Hua Zheng , Wei Xie , M. Ben Feng

We review an established Bayesian sampling method called sampling/importance resampling and highlight situations in nuclear theory when it can be particularly useful. To this end we both analyse a toy problem and demonstrate realistic…

Nuclear Theory · Physics 2023-01-18 Weiguang Jiang , Christian Forssén

In the search for more sample-efficient reinforcement-learning (RL) algorithms, a promising direction is to leverage as much external off-policy data as possible. For instance, expert demonstrations. In the past, multiple ideas have been…

Machine Learning · Computer Science 2023-03-01 Jesus Bujalance Martin , Fabien Moutarde

We provide theoretical investigations into off-policy evaluation in reinforcement learning using function approximators for (marginalized) importance weights and value functions. Our contributions include: (1) A new estimator, MWL, that…

Machine Learning · Computer Science 2020-10-08 Masatoshi Uehara , Jiawei Huang , Nan Jiang

We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem is often a critical step when applying RL…

Machine Learning · Computer Science 2016-05-27 Nan Jiang , Lihong Li

Sample efficiency is one of the most critical issues for online reinforcement learning (RL). Existing methods achieve higher sample efficiency by adopting model-based methods, Q-ensemble, or better exploration mechanisms. We, instead,…

Machine Learning · Computer Science 2023-05-31 Jiafei Lyu , Le Wan , Zongqing Lu , Xiu Li

Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the…

Machine Learning · Computer Science 2019-05-21 Guido Novati , Petros Koumoutsakos

In this paper we introduce Refractor Importance Sampling (RIS), an improvement to reduce error variance in Bayesian network importance sampling propagation under evidential reasoning. We prove the existence of a collection of importance…

Artificial Intelligence · Computer Science 2012-06-18 Haohai Yu , Robert A. van Engelen

Importance sampling (IS) is valuable in reducing the variance of Monte Carlo sampling for many areas, including finance, rare event simulation, and Bayesian inference. It is natural and obvious to combine quasi-Monte Carlo (QMC) methods…

Numerical Analysis · Mathematics 2022-07-21 Zhijian He , Zhan Zheng , Xiaoqun Wang
‹ Prev 1 4 5 6 7 8 10 Next ›