Research

Hello! I am a masters student at Harvard Computational Science. I am working on the application of inverse reinforcement learning and interpretable machine learning in healthcare. My advisor is Finale Doshi-velez.

Research Interests

My research focuses on the batch, off-policy, model-free inverse reinforcement learning and imitation learning in healthcare.

I have written peer-reviewed papers and a thesis on the problem of imitating and explaining experts in healthcare using Inverse Reinforcement Learning.

Publications

• Donghun Lee, Srivatsan Srinivasan, Finale Doshi-Velez, Truly Batch Apprenticeship Learning with Deep Successor Features (IJCAI, 2019) Link

Other research projects

I worked on a number of small research projects. For other technical projects, check this page out.

• Fairness and interpretation of black-box algorithmic decisions for peer-to-peer loan lending (done in collaboration with Square Capital).
• Evaluating the effect of adding Gradient noise on the learning performance of deep neural networks.
• Empirical Evaluation of Input-Convex Neural Network.
• Empirical Evaluation of Kernel-based Imitation Learning.
• Development of a Deep RL Poker Agent using Neural Fictious Self-Play.
• Tutorials on Least-Squares-Temporal-Difference (LSTD) and other reinforcement learning algorithms.
• Digital Silo (Google Summer of Code, 2017).