English
Related papers

Related papers: Two-way Deconfounder for Off-policy Evaluation in …

200 papers

We address the problem of causal effect estimation where hidden confounders are present, with a focus on two settings: instrumental variable regression with additional observed confounders, and proxy causal learning. Our approach uses a…

Machine Learning · Computer Science 2025-03-12 Haotian Sun , Antoine Moulin , Tongzheng Ren , Arthur Gretton , Bo Dai

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates the policy based on past observations, the samples are not…

Machine Learning · Computer Science 2020-10-27 Masahiro Kato , Yusuke Kaneko

Panel data are widely used in political science to draw causal inferences. However, these models often rely on the strong and untested assumption of sequential ignorability--that no unmeasured variables influence both the independent and…

Methodology · Statistics 2026-02-17 Bang Quan Zheng

Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…

Machine Learning · Computer Science 2022-12-19 Ashish Kumar , Ilya Kuzovkin

Off-Policy Evaluation (OPE) serves as one of the cornerstones in Reinforcement Learning (RL). Fitted Q Evaluation (FQE) with various function approximators, especially deep neural networks, has gained practical success. While statistical…

Machine Learning · Statistics 2022-02-11 Ruiqi Zhang , Xuezhou Zhang , Chengzhuo Ni , Mengdi Wang

Hidden confounders that influence both states and actions can bias policy learning in reinforcement learning (RL), leading to suboptimal or non-generalizable behavior. Most RL algorithms ignore this issue, learning policies from…

Machine Learning · Computer Science 2025-06-09 Thanh Vinh Vo , Young Lee , Haozhe Ma , Chien Lu , Tze-Yun Leong

As an important problem in causal inference, we discuss the estimation of treatment effects (TEs). Representing the confounder as a latent variable, we propose Intact-VAE, a new variant of variational autoencoder (VAE), motivated by the…

Machine Learning · Statistics 2022-04-22 Pengzhou Wu , Kenji Fukumizu

Offline reinforcement learning promises policy improvement from logged interaction data alone, yet state-of-the-art algorithms remain vulnerable to value over-estimation and to violations of domain knowledge such as monotonicity or…

Systems and Control · Electrical Eng. & Systems 2025-06-18 Ali Baheri

Causal inference from observational data requires assumptions. These assumptions range from measuring confounders to identifying instruments. Traditionally, causal inference assumptions have focused on estimation of effects for a single…

Machine Learning · Statistics 2019-03-04 Rajesh Ranganath , Adler Perotte

Algorithms are commonly used to predict outcomes under a particular decision or intervention, such as predicting whether an offender will succeed on parole if placed under minimal supervision. Generally, to learn such counterfactual…

Machine Learning · Statistics 2021-04-19 Amanda Coston , Edward H. Kennedy , Alexandra Chouldechova

Imitation learning from demonstrations usually suffers from the confounding effects of unmeasured variables (i.e., unmeasured confounders) on the states and actions. If ignoring them, a biased estimation of the policy would be entailed. To…

Machine Learning · Computer Science 2025-07-24 Yan Zeng , Shenglan Nie , Feng Xie , Libo Huang , Peng Wu , Zhi Geng

A major limitation of machine learning (ML) prediction models is that they recover associational, rather than causal, predictive relationships between variables. In high-stakes automation applications of ML this is problematic, as the model…

Machine Learning · Computer Science 2025-11-04 Jianqiao Mao , Max A. Little

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

When faced with sequential decision-making problems, it is often useful to be able to predict what would happen if decisions were made using a new policy. Those predictions must often be based on data collected under some previously used…

Machine Learning · Computer Science 2021-11-03 Yash Chandak , Scott Niekum , Bruno Castro da Silva , Erik Learned-Miller , Emma Brunskill , Philip S. Thomas

We show that the popular reinforcement learning (RL) strategy of estimating the state-action value (Q-function) by minimizing the mean squared Bellman error leads to a regression problem with confounding, the inputs and output noise being…

Machine Learning · Computer Science 2022-12-01 Yutian Chen , Liyuan Xu , Caglar Gulcehre , Tom Le Paine , Arthur Gretton , Nando de Freitas , Arnaud Doucet

Concept-based explanation approach is a popular model interpertability tool because it expresses the reasons for a model's predictions in terms of concepts that are meaningful for the domain experts. In this work, we study the problem of…

Machine Learning · Computer Science 2021-05-25 Mohammad Taha Bahadori , David E. Heckerman

A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific…

Robotics · Computer Science 2018-10-17 Gregory Kahn , Adam Villaflor , Pieter Abbeel , Sergey Levine

Context-based offline meta-reinforcement learning (OMRL) methods have achieved appealing success by leveraging pre-collected offline datasets to develop task representations that guide policy learning. However, current context-based OMRL…

Machine Learning · Computer Science 2025-02-04 Zhengzhe Zhang , Wenjia Meng , Haoliang Sun , Gang Pan

We study quantile-optimal policy learning where the goal is to find a policy whose reward distribution has the largest $\alpha$-quantile for some $\alpha \in (0, 1)$. We focus on the offline setting whose generating process involves…

Machine Learning · Statistics 2025-06-10 Zhongren Chen , Siyu Chen , Zhengling Qi , Xiaohong Chen , Zhuoran Yang

Model-based offline reinforcement learning approaches generally rely on bounds of model error. Estimating these bounds is usually achieved through uncertainty estimation methods. In this work, we combine parametric and nonparametric methods…

Machine Learning · Computer Science 2022-11-07 Guy Tennenholtz , Shie Mannor
‹ Prev 1 8 9 10 Next ›