17 citations · 71 across the 33 of their papers we have counts for
7 papers · 1 filter
Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings
Hengrui Cai, Chengchun Shi, Rui Song +1
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 dec…
Double Generative Adversarial Networks for Conditional Independence Testing
Chengchun Shi, Tianlin Xu, Wicher Bergsma +1
In this article, we study the problem of high-dimensional conditional independence testing, a key building block in statistics and machine learning. We propose an inferential proce…
Testing Mediation Effects Using Logic of Boolean Matrices
Chengchun Shi, Lexin Li
Mediation analysis is becoming an increasingly important tool in scientific studies. A central question in high-dimensional mediation analysis is to infer the significance of indiv…
Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making
Chengchun Shi, Runzhe Wan, Rui Song +2
The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning. In this paper, we propose a novel Forward-Backward Learning procedure to test MA in s…
Robust Reinforcement Learning via Adversarial training with Langevin Dynamics
Parameswaran Kamalaruban, Yu-Ting Huang, Ya-Ping Hsieh +3
We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynam…
Dynamic Causal Effects Evaluation in A/B Testing with a Reinforcement Learning Framework
Chengchun Shi, Xiaoyu Wang, Shikai Luo +3
A/B testing, or online experiment is a standard business strategy to compare a new product with an old one in pharmaceutical, technological, and traditional industries. Major chall…
Statistical Inference of the Value Function for Reinforcement Learning in Infinite Horizon Settings
C. Shi, S. Zhang, W. Lu +1
Reinforcement learning is a general technique that allows an agent to learn an optimal policy and interact with an environment in sequential decision making problems. The goodness…