English
Related papers

Related papers: Importance Resampling for Off-policy Prediction

200 papers

Off-policy estimation for long-horizon problems is important in many real-life applications such as healthcare and robotics, where high-fidelity simulators may not be available and on-policy evaluation is expensive or impossible. Recently,…

Machine Learning · Computer Science 2020-03-26 Ali Mousavi , Lihong Li , Qiang Liu , Denny Zhou

Off-policy evaluation often refers to two related tasks: estimating the expected return of a policy and estimating its value function (or other functions of interest, such as density ratios). While recent works on marginalized importance…

Machine Learning · Computer Science 2022-10-28 Audrey Huang , Nan Jiang

We consider the transfer of experience samples (i.e., tuples < s, a, s', r >) in reinforcement learning (RL), collected from a set of source tasks to improve the learning process in a given target task. Most of the related approaches focus…

Machine Learning · Computer Science 2018-05-29 Andrea Tirinzoni , Andrea Sessa , Matteo Pirotta , Marcello Restelli

Grid search and random search are widely used techniques for hyperparameter tuning in machine learning, especially when gradient information is unavailable. In these methods, a finite set of candidate configurations is evaluated, and the…

Optimization and Control · Mathematics 2026-04-06 Radu-Alexandru Dragomir , François Portier , Victor Priser

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning…

Off-policy evaluation (OPE) aims to estimate the benefit of following a counterfactual sequence of actions, given data collected from executed sequences. However, existing OPE estimators often exhibit high bias and high variance in problems…

Machine Learning · Computer Science 2023-07-17 Aaman Rebello , Shengpu Tang , Jenna Wiens , Sonali Parbhoo

In the time of Big Data, training complex models on large-scale data sets is challenging, making it appealing to reduce data volume for saving computation resources by subsampling. Most previous works in subsampling are weighted methods…

Machine Learning · Computer Science 2021-04-14 Zifeng Wang , Hong Zhu , Zhenhua Dong , Xiuqiang He , Shao-Lun Huang

By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spaces, the most popular methods for off-policy learning include…

Machine Learning · Computer Science 2023-12-01 Jared Markowitz , Jesse Silverberg , Gary Collins

Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse. In this paper, we show that the use of…

Machine Learning · Computer Science 2023-02-07 Zichuan Lin , Xiapeng Wu , Mingfei Sun , Deheng Ye , Qiang Fu , Wei Yang , Wei Liu

Multiple importance sampling (MIS) is an increasingly used methodology where several proposal densities are used to approximate integrals, generally involving target probability density functions. The use of several proposals allows for a…

Statistics Theory · Mathematics 2022-07-12 Rahul Mukerjee , Víctor Elvira

Learning effective contextual-bandit policies from past actions of a deployed system is highly desirable in many settings (e.g. voice assistants, recommendation, search), since it enables the reuse of large amounts of log data.…

Machine Learning · Computer Science 2020-06-18 Noveen Sachdeva , Yi Su , Thorsten Joachims

In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important…

Machine Learning · Computer Science 2016-04-05 Philip S. Thomas , Emma Brunskill

An essential problem in statistics and machine learning is the estimation of expectations involving PDFs with intractable normalizing constants. The self-normalized importance sampling (SNIS) estimator, which normalizes the IS weights, has…

Computation · Statistics 2024-07-01 Nicola Branchini , Víctor Elvira

We study the problem of evaluating the excess risk of large-scale empirical risk minimization under the square loss. Leveraging the idea of wild refitting and resampling, we assume only black-box access to the training algorithm and develop…

Machine Learning · Computer Science 2026-04-03 Haichen Hu , David Simchi-Levi

While reinforcement learning (RL) has shown promising performance, its sample complexity continues to be a substantial hurdle, restricting its broader application across a variety of domains. Imitation learning (IL) utilizes oracles to…

Machine Learning · Computer Science 2025-08-12 Xuefeng Liu , Takuma Yoneda , Rick L. Stevens , Matthew R. Walter , Yuxin Chen

Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience,…

Machine Learning · Computer Science 2019-03-21 Kate Rakelly , Aurick Zhou , Deirdre Quillen , Chelsea Finn , Sergey Levine

Recently, several approaches have been proposed to solve language generation problems. Transformer is currently state-of-the-art seq-to-seq model in language generation. Reinforcement Learning (RL) is useful in solving exposure bias and the…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Shiyang Yan , Yang Hua , Neil M. Robertson

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function space, as opposed to…

Machine Learning · Computer Science 2023-01-26 Naman Agarwal , Brian Bullins , Karan Singh

Adversarial Imitation Learning (AIL) is a class of algorithms in Reinforcement learning (RL), which tries to imitate an expert without taking any reward from the environment and does not provide expert behavior directly to the policy…

Machine Learning · Computer Science 2020-05-05 Samin Yeasar Arnob

Importance sampling is widely used to improve the efficiency of deep neural network (DNN) training by reducing the variance of gradient estimators. However, efficiently assessing the variance reduction relative to uniform sampling remains…

Machine Learning · Computer Science 2025-11-19 Takuro Kutsuna