Developing robust control policies for humanoid robots to navigate challenging terrains using deep reinforcement learning techniques. This work focuses on creating adaptive locomotion strategies that can handle various environmental obstacles and disturbances by replacing the diffusion model planner with a procedural generator equipped with a high-level policy.

Tools & Methods:

ContagionRL is a computational framework that simulates human behavioral responses during epidemics using reinforcement learning (RL). It combines a spatial Susceptible-Infected-Recovered-Susceptible (SIRS) disease model with a single-agent RL system, allowing agents to adapt their adherence to non-pharmaceutical interventions (NPIs) in real-time. The model integrates configurable parameters informed by mobility data and behavioral trends, enabling evaluation of public health policies and their impact on outbreak dynamics.

Tools & Methods:

An NLP-based system that automatically analyzes and maps entrepreneurship education programs and course syllabi against defined competency frameworks using zero-shot classification.

Tools & Methods:

A Monte Carlo protein optimization system that uses PyRosetta to systematically explore protein conformations and evaluate single amino acid mutations for enhanced stability and functionality.

Tools & Methods: