I’m studying artificial intelligence as a fourth year PhD student under George Konidaris
at Brown University.
Humans have the ability to seamlessly mix planning, learning, and communication, such that they can coordinate immensely complicated bodies to efficiently solve seemingly intractable problems.
Why can’t our algorithms do that yet?
To work towards that end, my research interests include model-based reinforcement learning, hierarchical reinforcement learning, and high-dimensional action abstraction.