English
Related papers

Related papers: Markovian Interference in Experiments

200 papers

We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data…

Machine Learning · Computer Science 2022-10-05 Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao

In many scenarios, such as the evaluation of place-based policies, potential outcomes are not only dependent upon the unit's own treatment but also its neighbors' treatment. Despite this, "difference-in-differences" (DID) type estimators…

Econometrics · Economics 2025-01-30 Ruonan Xu

This work introduces a non-intrusive model reduction approach for learning reduced models from partially observed state trajectories of high-dimensional dynamical systems. The proposed approach compensates for the loss of information due to…

Machine Learning · Computer Science 2021-03-29 Wayne Isaac Tan Uy , Benjamin Peherstorfer

Several problems in statistics involve the combination of high-variance unbiased estimators with low-variance estimators that are only unbiased under strong assumptions. A notable example is the estimation of causal effects while combining…

Methodology · Statistics 2023-05-25 Michael Oberst , Alexander D'Amour , Minmin Chen , Yuyan Wang , David Sontag , Steve Yadlowsky

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

Machine Learning · Computer Science 2020-02-25 Yaqi Duan , Mengdi Wang

Queue networks describe complex stochastic systems of both theoretical and practical interest. They provide the means to assess alterations, diagnose poor performance and evaluate robustness across sets of interconnected resources. In the…

Computation · Statistics 2017-11-02 Iker Perez , David Hodge , Theodore Kypraios

Model-based representations recently stand out as a promising framework that embeds latent dynamics information into the representations for downstream off-policy actor-critic learning. It implicitly combines the advantages of both…

Machine Learning · Computer Science 2026-05-13 Jiafei Lyu , Zichuan Lin , Scott Fujimoto , Kai Yang , Yangkun Chen , Saiyong Yang , Zongqing Lu , Deheng Ye

We introduce a novel doubly-robust (DR) off-policy evaluation (OPE) estimator for Markov decision processes, DRUnknown, designed for situations where both the logging policy and the value function are unknown. The proposed estimator…

Machine Learning · Statistics 2024-04-03 Kyungbok Lee , Myunghee Cho Paik

Stochastic optimal control of dynamical systems is a crucial challenge in sequential decision-making. Recently, control-as-inference approaches have had considerable success, providing a viable risk-sensitive framework to address the…

Machine Learning · Computer Science 2023-12-22 Hany Abdulsamad , Sahel Iqbal , Adrien Corenflos , Simo Särkkä

In offline reinforcement learning (RL) an optimal policy is learned solely from a priori collected observational data. However, in observational data, actions are often confounded by unobserved variables. Instrumental variables (IVs), in…

Machine Learning · Statistics 2024-10-16 Luofeng Liao , Zuyue Fu , Zhuoran Yang , Yixin Wang , Mladen Kolar , Zhaoran Wang

Researchers commonly use difference-in-differences (DiD) designs to evaluate public policy interventions. While methods exist for estimating effects in the context of binary interventions, policies often result in varied exposures across…

Methodology · Statistics 2025-02-07 Gary Hettinger , Youjin Lee , Nandita Mitra

We propose a novel approach to address one aspect of the non-stationarity problem in multi-agent reinforcement learning (RL), where the other agents may alter their policies due to environment changes during execution. This violates the…

Machine Learning · Computer Science 2019-12-03 Yixiang Wang , Feng Wu

Imitation learning practitioners have often noted that conditioning policies on previous actions leads to a dramatic divergence between "held out" error and performance of the learner in situ. Interactive approaches can provably address…

Machine Learning · Computer Science 2021-02-12 Jonathan Spencer , Sanjiban Choudhury , Arun Venkatraman , Brian Ziebart , J. Andrew Bagnell

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

We give an approach for characterizing interference by lower bounding the number of units whose outcome depends on selected groups of treated individuals, such as depending on the treatment of others, or others who are at least a certain…

Methodology · Statistics 2025-11-04 David Choi

This paper presents a randomization-based framework for estimating causal effects under interference between units, motivated by challenges that arise in analyzing experiments on social networks. The framework integrates three components:…

Statistics Theory · Mathematics 2018-06-21 Peter M. Aronow , Cyrus Samii

We propose a method for the algorithmic quantum simulation of memory effects described by integrodifferential evolution equations. It consists in the systematic use of perturbation theory techniques and a Markovian quantum simulator. Our…

Quantum Physics · Physics 2017-03-01 U. Alvarez-Rodriguez , R. Di Candia , J. Casanova , M. Sanz , E. Solano

Mediation analysis is an important analytic tool commonly used in a broad range of scientific applications. In this article, we study the problem of mediation analysis when there are multivariate and conditionally dependent mediators, and…

Methodology · Statistics 2025-01-28 Lan Luo , Chengchun Shi , Jitao Wang , Zhenke Wu , Lexin Li

Off-policy evaluation (OPE) in both contextual bandits and reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. The problem's importance…

Machine Learning · Computer Science 2019-06-11 Nathan Kallus , Masatoshi Uehara

Motivated by the novel paradigm developed by Van Roy and coauthors for reinforcement learning in arbitrary non-Markovian environments, we propose a related formulation and explicitly pin down the error caused by non-Markovianity of…

Systems and Control · Electrical Eng. & Systems 2024-02-15 Siddharth Chandak , Pratik Shah , Vivek S Borkar , Parth Dodhia