English
Related papers

Related papers: Markovian Interference in Experiments

200 papers

The focus of this paper is on stochastic variational inequalities (VI) under Markovian noise. A prominent application of our algorithmic developments is the stochastic policy evaluation problem in reinforcement learning. Prior…

Optimization and Control · Mathematics 2021-08-17 Georgios Kotsalis , Guanghui Lan , Tianjiao Li

Classical causal inference assumes treatments meant for a given unit do not have an effect on other units. This assumption is violated in interference problems, where new types of spillover causal effects arise, and causal inference becomes…

Methodology · Statistics 2024-09-30 Ilya Shpitser , Chan Park , Eric Tchetgen Tchetgen , Ryan Andrews

Differentiable simulators promise faster computation time for reinforcement learning by replacing zeroth-order gradient estimates of a stochastic objective with an estimate based on first-order gradients. However, it is yet unclear what…

Machine Learning · Computer Science 2022-08-23 H. J. Terry Suh , Max Simchowitz , Kaiqing Zhang , Russ Tedrake

This paper presents a novel model-free and fully data-driven policy iteration scheme for quadratic regulation of linear dynamics with state- and input-multiplicative noise. The implementation is similar to the least-squares temporal…

Optimization and Control · Mathematics 2022-12-05 Peter Coppens , Panagiotis Patrinos

Policy optimization has drawn increasing attention in reinforcement learning, particularly in the context of derivative-free methods for linear quadratic regulator (LQR) problems with unknown dynamics. This paper focuses on characterizing…

Optimization and Control · Mathematics 2025-06-17 Weijian Li , Panagiotis Kounatidis , Zhong-Ping Jiang , Andreas A. Malikopoulos

The convergence of policy gradient algorithms in reinforcement learning hinges on the optimization landscape of the underlying optimal control problem. Theoretical insights into these algorithms can often be acquired from analyzing those of…

Machine Learning · Computer Science 2023-11-01 Jingliang Duan , Wenhan Cao , Yang Zheng , Lin Zhao

We consider the problem of estimating a signal corrupted by independent interference with the assistance of a cost-constrained helper who knows the interference causally or noncausally. When the interference is known causally, we…

Information Theory · Computer Science 2012-03-21 Yeow-Khiang Chia , Rajiv Soundararajan , Tsachy Weissman

While on-policy algorithms are known for their stability, they often demand a substantial number of samples. In contrast, off-policy algorithms, which leverage past experiences, are considered sample-efficient but tend to exhibit…

Machine Learning · Computer Science 2023-09-28 Jianfei Ma

This paper studies how to design two-wave experiments in the presence of spillovers for precise inference on treatment effects. We consider units connected through a single network, local dependence among individuals, and a general class of…

Econometrics · Economics 2025-11-25 Davide Viviano

Optimal Markov Decision Process policies for problems with finite state and action space are identified through a partial ordering by comparing the value function across states. This is referred to as state-based optimality. This paper…

Optimization and Control · Mathematics 2021-12-02 Dylan Solms

A key challenge for robotic systems is to figure out the behavior of another agent. The capability to draw correct inferences is crucial to derive human behavior from examples. Processing correct inferences is especially challenging when…

Robotics · Computer Science 2022-07-19 Alexander Wich , Holger Schultheis , Michael Beetz

Indirect experiments provide a valuable framework for estimating treatment effects in situations where conducting randomized control trials (RCTs) is impractical or unethical. Unlike RCTs, indirect experiments estimate treatment effects by…

Machine Learning · Computer Science 2023-12-06 Yash Chandak , Shiv Shankar , Vasilis Syrgkanis , Emma Brunskill

Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate (low bias) gradient estimator is crucial to face…

Machine Learning · Computer Science 2022-03-09 Joao Carvalho , Jan Peters

We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators of varying performance. We assume the demonstrators are…

Machine Learning · Computer Science 2019-08-01 Pablo Samuel Castro , Shijian Li , Daqing Zhang

How should researchers analyze randomized experiments in which the main outcome is latent and measured in multiple ways but each measure contains some degree of error? We first identify a critical study-specific noncomparability problem in…

Econometrics · Economics 2026-01-13 Jiawei Fu , Donald P. Green

We consider a network of interacting agents and we model the process of choice on the adoption of a given innovative product by means of statistical-mechanics tools. The modelization allows us to focus on the effects of direct interactions…

Physics and Society · Physics 2015-02-24 Paolo Sgrignoli , Elena Agliari , Raffaella Burioni , Augusto Schianchi

This paper investigates a class of optimal control problems associated with Markov processes with local state information. The decision-maker has only local access to a subset of a state vector information as often encountered in…

Systems and Control · Electrical Eng. & Systems 2020-05-12 Guanze Peng , Veeraruna Kavitha , Qunayan Zhu

This paper considers the estimation of treatment effects in randomized experiments with complex experimental designs, including cases with interference between units. We develop a design-based estimation theory for arbitrary experimental…

Econometrics · Economics 2025-05-27 Haoge Chang

Our aim is to detect mechanistic interaction between the effects of two causal factors on a binary response, as an aid to identifying situations where the effects are mediated by a common mechanism. We propose a formalization of mechanistic…

Methodology · Statistics 2015-06-23 Carlo Berzuini , A. Philip Dawid

Focusing on stochastic systems arising in mean-field models, the systems under consideration belong to the class of switching diffusions, in which continuous dynamics and discrete events coexist and interact. The discrete events are modeled…

Probability · Mathematics 2019-01-18 Son L. Nguyen , George Yin , Tuan A. Hoang