Luke Strgar
I am a PhD student in AI and Robotics at Northwestern University, advised by Sam Kriegman in the Xenobot Lab. I have also spent time as a student researcher on the Paradigms of Intelligence team at Google.
I received my MSc. in Computer Science from the University of Texas at Austin, where I worked with David Harwath on self-supervised speech segmentation. Before that, I earned my B.A. in Computer Science from the University of California at Berkeley.
Research
I research intelligent systems that adapt across multiple scales in time and space. Biological organisms evolve over generations, learn extensively during their lifetimes, and are composed of layers of intelligent components — organs, cells, protiens. These intertwined processes and hierarchies shape the bodies, brains, and behaviors of living things. To study this interplay, I develop algorithms and simulations that jointly optimize the bodies and brains of artificial agents to achieve adaptive behavior. A key innovation is that my simulations are differentiable, allowing agents to learn from exact gradients propagated through physical simulation rather than the costly trial-and-error sampling that reinforcement learning requires.