|
Michael Littman
Computer Science Department, Rutgers, USA
Wednesday 31 March 2010
16.00
Seminar Room B10 (Basement)
Alexandra House, 17 Queen Square, London, WC1N 3AR
Efficiently Learning to Behave Efficiently
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 via a new framework we call KWIK (Knows What It Knows) learning. I'll summarize the framework, our algorithms, their formal validations, and their empirical evaluations in robotic and videogame testbeds. This approach holds promise for attacking challenging problems in a number of application domains.