English
Related papers

Related papers: Scaling Marginalized Importance Sampling to High-D…

200 papers

Doubly robust methods hold considerable promise for off-policy evaluation in Markov decision processes (MDPs) under sequential ignorability: They have been shown to converge as $1/\sqrt{T}$ with the horizon $T$, to be statistically…

Machine Learning · Statistics 2025-09-30 Mohammad Mehrabi , Stefan Wager

We study the offline reinforcement learning (RL) in the face of unmeasured confounders. Due to the lack of online interaction with the environment, offline RL is facing the following two significant challenges: (i) the agent may be…

Machine Learning · Computer Science 2022-09-20 Zuyue Fu , Zhengling Qi , Zhaoran Wang , Zhuoran Yang , Yanxun Xu , Michael R. Kosorok

We study the off-policy evaluation (OPE) problem in an infinite-horizon Markov decision process with continuous states and actions. We recast the $Q$-function estimation into a special form of the nonparametric instrumental variables (NPIV)…

Statistics Theory · Mathematics 2022-06-28 Xiaohong Chen , Zhengling Qi

This paper explores the impact of relational state abstraction on sample efficiency and performance in collaborative Multi-Agent Reinforcement Learning. The proposed abstraction is based on spatial relationships in environments where direct…

Artificial Intelligence · Computer Science 2025-04-23 Sharlin Utke , Jeremie Houssineau , Giovanni Montana

We consider off-policy evaluation (OPE) in continuous treatment settings, such as personalized dose-finding. In OPE, one aims to estimate the mean outcome under a new treatment decision rule using historical data generated by a different…

Machine Learning · Statistics 2021-11-08 Hengrui Cai , Chengchun Shi , Rui Song , Wenbin Lu

Off-policy estimation (OPE) methods enable unbiased offline evaluation of recommender systems, directly estimating the online reward some target policy would have obtained, from offline data and with statistical guarantees. The theoretical…

Machine Learning · Statistics 2025-08-12 Olivier Jeunen

This paper concerns the central issues of model robustness and sample efficiency in offline reinforcement learning (RL), which aims to learn to perform decision making from history data without active exploration. Due to uncertainties and…

Machine Learning · Computer Science 2024-01-01 Laixi Shi , Yuejie Chi

State estimation is key to both analyzing physical mechanisms and enabling real-time control of fluid flows. A common estimation approach is to relate sensor measurements to a reduced state governed by a reduced-order model (ROM). (When…

Fluid Dynamics · Physics 2020-06-10 Nirmal J. Nair , Andres Goza

Reinforcement learning can train policies that effectively perform complex tasks. However for long-horizon tasks, the performance of these methods degrades with horizon, often necessitating reasoning over and chaining lower-level skills.…

Machine Learning · Computer Science 2022-03-31 Dhruv Shah , Peng Xu , Yao Lu , Ted Xiao , Alexander Toshev , Sergey Levine , Brian Ichter

Reinforcement Learning (RL) has demonstrated tremendous empirical success across numerous challenging domains. However, we lack a strong theoretical understanding of the statistical complexity of RL in environments with large state spaces,…

Machine Learning · Computer Science 2025-06-03 Gene Li

Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works primarily focus on incorporating pessimism for policy…

Machine Learning · Computer Science 2024-01-12 Yuanzhao Zhai , Yiying Li , Zijian Gao , Xudong Gong , Kele Xu , Dawei Feng , Ding Bo , Huaimin Wang

In this work we propose techniques for efficient reachability analysis of the state space (e.g., detection of bad states) using a combination of partial order and symmetry based reductions in a distributed setting. The proposed techniques…

Distributed, Parallel, and Cluster Computing · Computer Science 2009-01-05 Janardan Misra , Suman Roy

Offline Reinforcement Learning (RL) methods leverage previous experiences to learn better policies than the behavior policy used for data collection. However, they face challenges handling distribution shifts due to the lack of online…

Machine Learning · Computer Science 2025-06-09 Suzan Ece Ada , Erhan Oztop , Emre Ugur

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

Offline reinforcement learning seeks to utilize offline (observational) data to guide the learning of (causal) sequential decision making strategies. The hope is that offline reinforcement learning coupled with function approximation…

Machine Learning · Computer Science 2020-10-23 Ruosong Wang , Dean P. Foster , Sham M. Kakade

In systems governed by nonlinear partial differential equations such as fluid flows, the design of state estimators such as Kalman filters relies on a reduced-order model (ROM) that projects the original high-dimensional dynamics onto a…

Machine Learning · Computer Science 2024-04-05 Saviz Mowlavi , Mouhacine Benosman

In this paper, we present a novel optimization algorithm designed specifically for estimating state-space models to deal with heavy-tailed measurement noise and constraints. Our algorithm addresses two significant limitations found in…

Signal Processing · Electrical Eng. & Systems 2024-11-19 Yifan Yu , Shengjie Xiu , Daniel P. Palomar

We consider the problem of offline reinforcement learning (RL) -- a well-motivated setting of RL that aims at policy optimization using only historical data. Despite its wide applicability, theoretical understandings of offline RL, such as…

Machine Learning · Computer Science 2021-02-04 Ming Yin , Yu Bai , Yu-Xiang Wang

This work studies a Reinforcement Learning (RL) problem in which we are given a set of trajectories collected with K baseline policies. Each of these policies can be quite suboptimal in isolation, and have strong performance in…

Machine Learning · Computer Science 2024-03-29 Teodor V. Marinov , Alekh Agarwal , Mircea Trofin

Off-policy evaluation (OPE) is important for closing the gap between offline training and evaluation of reinforcement learning (RL), by estimating performance and/or rank of target (evaluation) policies using offline trajectories only. It…

Machine Learning · Computer Science 2023-10-17 Qitong Gao , Ge Gao , Juncheng Dong , Vahid Tarokh , Min Chi , Miroslav Pajic
‹ Prev 1 8 9 10 Next ›