Learning solutions to adversarial games with limited compute
Finding saddle points in zero-sum games via modified Q-learning 
Portfolio
Decision-making in changing environments
Regret minimization in the face of non-stationarities 
Experiment design for reducing uncertainty where it matters most
Stochastic optimization approach to task-oriented experiment design 
Learning car dynamics from repeated tasks
Stochastic Model Predictive Control with Gaussian Process regression for learning dynamics 
Secondary control in microgrids for voltage restoration
Distributed Nonlinear Model Predictive Control (DNMPC) for autonomous droop-controlled inverter-based microgrids
Electric vehicle charge scheduling from a multi-stakeholder perspective
Formulating and solving a mixed-integer quadratic program (MIQP)
Supervisory safety controller for preventing collisions of an inverted pendulum mass-cart system
Using reachability methods based on set theory to define a safety controller/filter 
Recovery of heat from drain water in residental settings
Active control of heat exchangers in a cyber-physical system 
Magnetic levitation of a steel bearing
Full analog control with op amp 