Date: Jan 22nd, 2009
Room: DMP 310
Speaker: Michael Littman
Title: Efficiently Learning to Behave Efficiently

Abstract:

The field of reinforcement learning is concerned with the problem of learning efficient behavior from experience. In real life applications, gathering this experience is time-consuming and possibly costly, so it is critical to derive algorithms that can learn effective behavior with bounds on the experience necessary to do so. This talk presents our successful efforts to create such algorithms within a framework known as "PAC-MDP". I'll summarize the framework, our algorithms, their formal validations, and their empirical evaluations in robotic and videogame testbeds.