I’m an Assistant Professor at NYU Tandon based in Civil Engineering and an affiliation with Computer Science. I received my PhD in control and reinforcement learning from UC Berkeley with Alexandre Bayen during which I spent time at Apple, Tesla, Deepmind, and Facebook AI Research. My research goal is to see complex, human-like behavior emerge from unsupervised interaction between groups of learning agents. We often apply algorithms and agents designed in this way, through large-scale self-play, to robotics and transportation. Concretely this leads to a lot of questions I’m currently interested in:

• How can we use RL to design models of human agents? How can we ensure that RL designed agents are human-compatible?
• How can we synthesize environments that push and test the capabilities of our agents?
• What missing algorithmic advances and software tools are keeping RL from scaling?

In practice this means working on understanding how to push the state of the art in multi-agent RL algorithms, designing new data-driven simulators, and trying to deploy simulator-designed controllers into real-world systems.