I'm in the job market for a postdoc! Check out my CV and research statement.
I'm a PhD student at UMass Amherst under Shlomo Zilberstein interested in building autonomous systems that can operate in natural, partially observable, stochastic domains for long periods of time.
Recently, I won a Distinguished Paper Award at AAAI, received an NSF Graduate Research Fellowship, and was a Distinguished Teaching Award Finalist at UMass Amherst.
At a high level, I focus on ethical compliance, efficient planning, and reliable execution in autonomous systems.
How can an autonomous system encode a given ethical theory?
How can an autonomous system comply with a given ethical theory?
How can an autonomous system determine when to interrupt its planner?
How can an autonomous system tune the hyperparameters of its planner?
How can an autonomous system recover from exceptional scenarios?
How can an autonomous system maintain and restore safe operation?