Dissertation Talk: Generalization via Self-Directed Learning

Presentation | May 17 | 12-1 p.m. | Soda Hall, 510 (VCL)

 Deepak Pathak, Computer Science, UC Berkeley

 Electrical Engineering and Computer Sciences (EECS)

Generalization, i.e., the ability to adapt to novel scenarios, is the hallmark of human intelligence. While we have systems that excel at recognizing objects, cleaning floors, playing complex games and occasionally beating humans, they are incredibly specific in that they only perform the tasks they are trained for and are miserable at generalization. Could actually optimizing towards fixed external goals be hindering the generalization instead of aiding it? In this talk, I will present our initial efforts toward endowing artificial agents with a human-like ability to generalize in diverse scenarios. The main insight is to first allow the agent to learn general-purpose skills in a completely self-directed manner, without optimizing for any external goal. These skills are then later repurposed to perform complex tasks. I will discuss how this framework can be instantiated to develop curiosity-driven agents (virtual as well as real) that can learn to play games, learn to walk, and learn to perform real-world object manipulation without any rewards or supervision. These self-directed robotic agents, after exploring the environment, can generalize to find their way in office environments, tie knots using rope, rearrange object configuration, and compose their skills in a modular fashion.

 pathak@berkeley.edu