Type:        Startup

Program:  Missile Defense Agency - MDA22-T004:
                 Deep Reinforcement Learning Enabled                  Warfighter Assistant

Duration:  May 2022 - Present

Architected a full-stack framework of explainable deep reinforcement learning for missile defense, centered on a novel method of Neural Tree Extraction and Perturbations (NTEP) to synthesize and enhance insights from SHAP and LIME;

Developed prototype agents for command, control, and engagement tasks in regional missile defense, countering the high unpredictability and limited decision times with robust training;

Submitted a full Phase I proposal for topic MDA22-T004, with comprehensive strategies and daily plans for R&D and commercialization for military and private sector customers.

The Targeted Level of Expressiveness in DRL Explanations:





























Return to Top
Return to Home