Picture for Alizée Pace

Alizée Pace

Uncertainty-Penalized Direct Preference Optimization

Add code
Oct 26, 2024
Viaarxiv icon

Preference Elicitation for Offline Reinforcement Learning

Add code
Jun 26, 2024
Figure 1 for Preference Elicitation for Offline Reinforcement Learning
Figure 2 for Preference Elicitation for Offline Reinforcement Learning
Figure 3 for Preference Elicitation for Offline Reinforcement Learning
Figure 4 for Preference Elicitation for Offline Reinforcement Learning
Viaarxiv icon

West-of-N: Synthetic Preference Generation for Improved Reward Modeling

Add code
Jan 22, 2024
Viaarxiv icon

On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series

Add code
Nov 15, 2023
Viaarxiv icon

Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding

Add code
Jun 01, 2023
Viaarxiv icon

Temporal Label Smoothing for Early Prediction of Adverse Events

Add code
Aug 29, 2022
Figure 1 for Temporal Label Smoothing for Early Prediction of Adverse Events
Figure 2 for Temporal Label Smoothing for Early Prediction of Adverse Events
Figure 3 for Temporal Label Smoothing for Early Prediction of Adverse Events
Figure 4 for Temporal Label Smoothing for Early Prediction of Adverse Events
Viaarxiv icon

POETREE: Interpretable Policy Learning with Adaptive Decision Trees

Add code
Mar 15, 2022
Figure 1 for POETREE: Interpretable Policy Learning with Adaptive Decision Trees
Figure 2 for POETREE: Interpretable Policy Learning with Adaptive Decision Trees
Figure 3 for POETREE: Interpretable Policy Learning with Adaptive Decision Trees
Figure 4 for POETREE: Interpretable Policy Learning with Adaptive Decision Trees
Viaarxiv icon