Reproducible Code
Code accompanying my research papers, providing reproducible implementations of the proposed methods and simulation studies.
Near-Equivalent Q-learning Policies for Dynamic Treatment Regimes
Research code accompanying ongoing work on near-equivalent treatment policies in reinforcement learning for dynamic treatment regimes.
Methods: reinforcement learning, dynamic treatment regimes
Language: Python
Bayesian Outcome-Weighted Learning
Code accompanying my work on Bayesian outcome-weighted learning, focusing on uncertainty quantification for treatment rule estimation.
Methods: Bayesian inference, outcome-weighted learning
Language: Python
Preprint • Code coming soon
Rewards Construction Based on Preference Learning for Dynamic Treatment Regimes
Research code for preference-based reward construction in reinforcement learning for dynamic treatment regimes.
Methods: preference learning, reinforcement learning, dynamic treatment regimes
Language: Python
Code coming soon