Faculty Candidate Seminar|
Learning Hierarchical Control Programs
University of California, Berkeley
Thursday, April 11, 2019|
10:30am - 11:30am
Add to Google Calendar
About the Event
Machine learning is, in a sense, data-driven programming: the execution of coded programs is replaced by the evaluation of learned models. In this talk, I will propose leveraging decades of hard-earned programming wisdom by imposing a hierarchical structure on deep-learnable models. I will introduce Parametrized Hierarchical Procedures (PHP), a neural network architecture with improved data efficiency, interpretability, and reusability — in analogy to similar benefits for human coders who adhere to the procedural programming paradigm. This line of work focuses on two application domains, robot control and algorithmic program induction, in which the control program interacts with physical environments and memory structures, respectively, through a sequence of API calls to readers (sensors) and writers (motors). We collect data demonstrating correct interaction, and use it to learn a program, represented as a PHP, that can perform the task.
Roy Fox is a postdoc at UC Berkeley AI Research (BAIR), working with Ion Stoica in the RISELab and with Ken Goldberg in the AUTOLAB. His research interests include reinforcement learning, dynamical systems, information theory, and robotics. His current research focuses on data-driven discovery of hierarchical control structures in deep reinforcement and imitation learning of robotic tasks. Roy has a MSc in Computer Science with Moshe Tennenholtz at the Technion, and a PhD in Computer Science with Naftali Tishby at the Hebrew University. He was an exchange PhD student with Larry Abbott and Liam Paninski at Columbia University, and a research intern at Microsoft Research.
Open to: Public