Picture for Shengpu Tang

Shengpu Tang

Division of Computer Science & Engineering, University of Michigan

Machine Learning for Health symposium 2023 -- Findings track

Dec 01, 2023
Viaarxiv icon

Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation

Add code
Oct 26, 2023
Figure 1 for Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
Figure 2 for Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
Figure 3 for Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
Figure 4 for Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
Viaarxiv icon

Leveraging Factored Action Spaces for Off-Policy Evaluation

Add code
Jul 13, 2023
Figure 1 for Leveraging Factored Action Spaces for Off-Policy Evaluation
Figure 2 for Leveraging Factored Action Spaces for Off-Policy Evaluation
Figure 3 for Leveraging Factored Action Spaces for Off-Policy Evaluation
Figure 4 for Leveraging Factored Action Spaces for Off-Policy Evaluation
Viaarxiv icon

Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare

Add code
May 02, 2023
Figure 1 for Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
Figure 2 for Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
Figure 3 for Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
Figure 4 for Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
Viaarxiv icon

Machine Learning for Health symposium 2022 -- Extended Abstract track

Nov 28, 2022
Viaarxiv icon

Towards Data-Driven Offline Simulations for Online Reinforcement Learning

Add code
Nov 14, 2022
Figure 1 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Figure 2 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Figure 3 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Figure 4 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Viaarxiv icon

Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings

Add code
Jul 23, 2021
Figure 1 for Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
Figure 2 for Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
Figure 3 for Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
Figure 4 for Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
Viaarxiv icon

Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies

Add code
Jul 24, 2020
Figure 1 for Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
Figure 2 for Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
Figure 3 for Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
Figure 4 for Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
Viaarxiv icon

Relaxed Weight Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series

Add code
Jun 07, 2019
Figure 1 for Relaxed Weight Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series
Figure 2 for Relaxed Weight Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series
Figure 3 for Relaxed Weight Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series
Figure 4 for Relaxed Weight Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series
Viaarxiv icon