Assistant Professor of Computer Science at Princeton University.
Affiliated/Associated Faculty with the Princeton Program in Cognitive Science and the Princeton Language Initiative.
Before joining Princeton, he completed his PhD in machine learning at Carnegie Mellon University (CMU) under the guidance of Ruslan Salakhutdinov and Sergey Levine, with support from the NSF Graduate Research Fellowship Program (GFRP) and the Hertz Fellowship. He spent several years at Google Brain/Research both before and during his PhD. His undergraduate studies were in mathematics at MIT.
Lecture: Introduction to Reinforcement Learning
Reinforcement learning (RL) is a machine learning technique that teaches agents how to make decisions that lead to good outcomes. These three lectures will introduce the mathematical formalism for describing optimal decision making, highlight key algorithmic ideas, and will touch briefly upon recent advances. These lectures will introduce foundational concepts that will be used in the subsequent lectures on RL and robot learning.