Picture for Shikai Luo

Shikai Luo

Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences

Add code
Jul 25, 2024
Figure 1 for Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences
Figure 2 for Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences
Figure 3 for Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences
Figure 4 for Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences
Viaarxiv icon

Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data

Add code
Mar 18, 2024
Viaarxiv icon

Robust Offline Policy Evaluation and Optimization with Heavy-Tailed Rewards

Add code
Oct 28, 2023
Viaarxiv icon

Quantile Off-Policy Evaluation via Deep Conditional Generative Learning

Add code
Dec 29, 2022
Viaarxiv icon

An Instrumental Variable Approach to Confounded Off-Policy Evaluation

Add code
Dec 29, 2022
Viaarxiv icon

Conformal Off-Policy Prediction

Add code
Jun 14, 2022
Figure 1 for Conformal Off-Policy Prediction
Figure 2 for Conformal Off-Policy Prediction
Figure 3 for Conformal Off-Policy Prediction
Viaarxiv icon

Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process

Add code
Mar 12, 2022
Figure 1 for Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process
Figure 2 for Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process
Figure 3 for Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process
Figure 4 for Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process
Viaarxiv icon

Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons

Add code
Feb 26, 2022
Figure 1 for Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons
Figure 2 for Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons
Figure 3 for Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons
Figure 4 for Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons
Viaarxiv icon

Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms

Add code
Feb 22, 2022
Figure 1 for Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms
Figure 2 for Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms
Figure 3 for Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms
Figure 4 for Policy Evaluation for Temporal and/or Spatial Dependent Experiments in Ride-sourcing Platforms
Viaarxiv icon

A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets

Add code
Feb 21, 2022
Figure 1 for A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets
Figure 2 for A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets
Figure 3 for A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets
Figure 4 for A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets
Viaarxiv icon