Search Results for author:
Found 36 papers, 18 papers with code
An Analysis of Switchback Designs in Reinforcement Learning
Our aim is to thoroughly evaluate the effects of these designs on the accuracy of their resulting average treatment effect (ATE) estimators.
Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data
As a result, leveraging large observational datasets becomes a more attractive option for achieving high-quality policy learning.
Robust Offline Reinforcement learning with Heavy-Tailed Rewards
This paper endeavors to augment the robustness of offline reinforcement learning (RL) in scenarios laden with heavy-tailed rewards, a prevalent circumstance in real-world applications.
Off-policy Evaluation in Doubly Inhomogeneous Environments
This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated.
Testing for the Markov Property in Time Series via Deep Conditional Generative Learning
In this article, we propose a nonparametric test for the Markov property in high-dimensional time series via deep conditional generative learning.
Evaluating Dynamic Conditional Quantile Treatment Effects with Applications in Ridesharing
However, assessing dynamic quantile treatment effects (QTE) remains a challenge, particularly when dealing with data from ride-sourcing platforms that involve sequential decision-making across time and space.
Sequential Knockoffs for Variable Selection in Reinforcement Learning
In real-world applications of reinforcement learning, it is often challenging to obtain a state representation that is parsimonious and satisfies the Markov property without prior knowledge.
A Reinforcement Learning Framework for Dynamic Mediation Analysis
However, there are a number of applications (e. g., mobile health) where the treatments are sequentially assigned over time and the dynamic mediation effects are of primary interest.
Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization
When the initial policy is consistent, under some mild conditions, our method will yield a policy whose value converges to the optimal one at a faster rate than the initial policy, achieving the desired ``value enhancement" property.
Deep Spectral Q-learning with Application to Mobile Health
Dynamic treatment regimes assign personalized treatments to patients sequentially over time based on their baseline information and time-varying covariates.
Quantile Off-Policy Evaluation via Deep Conditional Generative Learning
Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy.
An Instrumental Variable Approach to Confounded Off-Policy Evaluation
Off-policy evaluation (OPE) is a method for estimating the return of a target policy using some pre-collected observational data generated by a potentially different behavior policy.
A Review of Off-Policy Evaluation in Reinforcement Learning
Reinforcement learning (RL) is one of the most vibrant research frontiers in machine learning and has been recently applied to solve a number of challenging problems.
Doubly Inhomogeneous Reinforcement Learning
Moreover, by borrowing information over time and population, it allows us to detect weaker signals and has better convergence properties when compared to applying the clustering algorithm per time or the change point detection algorithm per subject.
Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach
In this article, we propose a novel pessimism-based Bayesian learning method for optimal dynamic treatment regimes in the offline setting.
Blessing from Human-AI Interaction: Super Reinforcement Learning in Confounded Environments
This approach utilizes the observed action, either from AI or humans, as input for achieving a stronger oracle in policy learning for the decision maker (humans or AI).
Semi-supervised Batch Learning From Logged Data
We propose learning methods for problems where feedback is missing for some samples, so there are samples with feedback and samples missing-feedback in the logged data.
Future-Dependent Value-Based Off-Policy Evaluation in POMDPs
Finally, we extend our methods to learning of dynamics and establish the connection between our approach and the well-known spectral learning methods in POMDPs.
Conformal Off-policy Prediction
Off-policy evaluation is critical in a number of applications where new policies need to be evaluated offline before online deployment.
Testing Stationarity and Change Point Detection in Reinforcement Learning
Based on the proposed test, we further develop a sequential change point detection method that can be naturally coupled with existing state-of-the-art RL methods for policy optimization in nonstationary environments.
Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons
We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications.
Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process
In this paper, we show that with some auxiliary variables that mediate the effect of actions on the system dynamics, the target policy's value is identifiable in a confounded Markov decision process.
Policy Evaluation for Temporal and/or Spatial Dependent Experiments
The aim of this paper is to establish a causal link between the policies implemented by technology companies and the outcomes they yield within intricate temporal and/or spatial dependent experiments.
A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets
In this paper we consider large-scale fleet management in ride-sharing companies that involve multiple units in different areas receiving sequences of products (or treatments) over time.
Jump Interval-Learning for Individualized Decision Making
To derive an optimal I2DR, our jump interval-learning method estimates the conditional mean of the outcome given the treatment and the covariates via jump penalized regression, and derives the corresponding optimal I2DR based on the estimated outcome regression function.
A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes
In this work, we first propose novel identification methods for OPE in POMDPs with latent confounders, by introducing bridge functions that link the target policy's value and the observed data distribution.
Testing Directed Acyclic Graph via Structural, Supervised and Generative Adversarial Learning
In this article, we propose a new hypothesis testing method for directed acyclic graph (DAG).
Pattern Transfer Learning for Reinforcement Learning in Order Dispatching
Order dispatch is one of the central problems to ride-sharing platforms.
Deeply-Debiased Off-Policy Interval Estimation
Off-policy evaluation learns a target policy's value with a historical dataset generated by a different behavior policy.
A REINFORCEMENT LEARNING FRAMEWORK FOR TIME DEPENDENT CAUSAL EFFECTS EVALUATION IN A/B TESTING
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.
Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings
To handle continuous treatments, we develop a novel estimation method for OPE using deep jump learning.
Deep Jump Q-Evaluation for Offline Policy Evaluation in Continuous Action Space
To handle continuous action space, we develop a brand-new deep jump Q-evaluation method for OPE.
Double Generative Adversarial Networks for Conditional Independence Testing
In this article, we study the problem of high-dimensional conditional independence testing, a key building block in statistics and machine learning.
Dynamic Causal Effects Evaluation in A/B Testing with a Reinforcement Learning Framework
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.
Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making
The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning.
Robust Learning for Optimal Treatment Decision with NP-Dimensionality
In this paper, we propose a two-step estimation procedure for deriving the optimal treatment regime under NP dimensionality.
