Sequential Decision Making
Modeling and solving sequential problems under uncertainty using dynamic programming, approximate dynamic programming, MDPs, and SMDPs.
View related work →Research
My research sits at the intersection of operations research, reinforcement learning, and stochastic systems. I focus on designing algorithms with theoretical structure and evaluating them in realistic simulation environments.
Reinforcement Learning
Theory and algorithms for learning control policies in stochastic operational systems, with attention to stability, constraints, and interpretability.
View related work →Simulation & Evaluation
Building high-fidelity environments to validate policies, understand behavior, and guide decision-making before deployment.
View related work →Stochastic Optimization
Developing tractable decision models under uncertainty for operations, reliability, service systems, and logistics.
View related work →