English
Related papers

Related papers: Markovian Interference in Experiments

200 papers

N-of-1 experiments, where a unit serves as its own control and treatment in different time windows, have been used in certain medical contexts for decades. However, due to effects that accumulate over long time windows and interventions…

Methodology · Statistics 2025-02-25 Tengyuan Liang , Benjamin Recht

Multi-Agent Reinforcement Learning involves agents that learn together in a shared environment, leading to emergent dynamics sensitive to initial conditions and parameter variations. A Dynamical Systems approach, which studies the evolution…

Multiagent Systems · Computer Science 2025-01-03 David Goll , Jobst Heitzig , Wolfram Barfuss

Accurate estimation of treatment effects is essential for decision-making across various scientific fields. This task, however, becomes challenging in areas like social sciences and online marketplaces, where treating one experimental unit…

Machine Learning · Computer Science 2025-02-04 Mohsen Bayati , Yuwei Luo , William Overman , Sadegh Shirani , Ruoxuan Xiong

In experiments that study social phenomena, such as peer influence or herd immunity, the treatment of one unit may influence the outcomes of others. Such "interference between units" violates traditional approaches for causal inference, so…

Methodology · Statistics 2023-08-30 David Choi

An experimental unit is an opportunity to randomly apply or withhold a treatment. There is interference between units if the application of the treatment to one unit may also affect other units. In cognitive neuroscience, a common form of…

Methodology · Statistics 2017-01-11 Xi Luo , Dylan S. Small , Chiang-shan R. Li , Paul R. Rosenbaum

We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another policy(ies). In particular, we focus on the doubly robust (DR)…

Artificial Intelligence · Computer Science 2018-05-25 Mehrdad Farajtabar , Yinlam Chow , Mohammad Ghavamzadeh

In policy gradient reinforcement learning, access to a differentiable model enables 1st-order gradient estimation that accelerates learning compared to relying solely on derivative-free 0th-order estimators. However, discontinuous dynamics…

Machine Learning · Computer Science 2026-04-21 Ku Onoda , Paavo Parmas , Manato Yaguchi , Yutaka Matsuo

Markovian processes have long been used to model stochastic environments. Reinforcement learning has emerged as a framework to solve sequential planning and decision-making problems in such environments. In recent years, attempts were made…

Artificial Intelligence · Computer Science 2014-01-17 Mahdi Milani Fard , Joelle Pineau

Catastrophic interference is common in many network-based learning systems, and many proposals exist for mitigating it. Before overcoming interference we must understand it better. In this work, we provide a definition and novel measure of…

Machine Learning · Computer Science 2023-07-12 Vincent Liu , Han Wang , Ruo Yu Tao , Khurram Javed , Adam White , Martha White

Attention models have had a significant positive impact on deep learning across a range of tasks. However previous attempts at integrating attention with reinforcement learning have failed to produce significant improvements. We propose the…

Machine Learning · Computer Science 2019-04-09 Anthony Manchin , Ehsan Abbasnejad , Anton van den Hengel

We observe n possibly dependent random variables, the distribution of which is presumed to be stationary even though this might not be true, and we aim at estimating the stationary distribution. We establish a non-asymptotic deviation bound…

Statistics Theory · Mathematics 2023-07-10 Alexandre Lecestre

Classical approaches to experimental design assume that intervening on one unit does not affect other units. There are many important settings, however, where this non-interference assumption does not hold, as when running experiments on…

Optimization and Control · Mathematics 2020-07-01 Stefan Wager , Kuang Xu

We provide performance guarantees for a variant of simulation-based policy iteration for controlling Markov decision processes that involves the use of stochastic approximation algorithms along with state-of-the-art techniques that are…

Machine Learning · Computer Science 2022-10-17 Anna Winnicki , R. Srikant

The separation of the Schr\"{o}dinger equation into a Markovian and an interference term provides a new insight in the quantum dynamics of classically chaotic systems. The competition between these two terms determines the localized or…

Quantum Physics · Physics 2009-11-07 A. Romanelli , A. C. Sicardi Schifino , G. Abal , R. Siri , R. Donangelo

We propose a comprehensive framework for policy gradient methods tailored to continuous time reinforcement learning. This is based on the connection between stochastic control problems and randomised problems, enabling applications across…

Optimization and Control · Mathematics 2024-05-01 Robert Denkert , Huyên Pham , Xavier Warin

Although there is now a large literature on policy evaluation and learning, much of the prior work assumes that the treatment assignment of one unit does not affect the outcome of another unit. Unfortunately, ignoring interference can lead…

Methodology · Statistics 2025-04-02 Yi Zhang , Kosuke Imai

Classical designs of randomized experiments, going back to Fisher and Neyman in the 1930s still dominate practice even in online experimentation. However, such designs are of limited value for answering standard questions in settings,…

Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…

Robotics · Computer Science 2022-05-10 Hirotaka Tahara , Hikaru Sasaki , Hanbit Oh , Brendan Michael , Takamitsu Matsubara

In randomized experiments, covariates are often used to reduce variance and improve the precision of treatment effect estimates. However, in many real-world settings, interference between units, where one unit's treatment affects another's…

Methodology · Statistics 2026-04-10 Xinyi Wang , Shuangning Li

In this work, we present the first finite-time analysis of Q-learning with time-varying learning policies (i.e., on-policy sampling) for discounted Markov decision processes under minimal assumptions, requiring only the existence of a…

Machine Learning · Computer Science 2026-04-07 Phalguni Nanda , Zaiwei Chen