[Colloq] Hiring Talk Tuesday, March 12, 11am, 149CN

Rachel Bates rachelb at ccs.neu.edu
Thu, 7 Mar 2002 11:51:35 -0500


The College of Computer Science Presents:
Satinder Singh

will speak on:
Reinforcement Learning Formulations of the AI Problem: Have they been good
for AI?
			      OR
	(An Analysis of the Exploitation-Exploration Tradeoff and an Application to
Human-Computer Interaction)

Tuesday, March 12, 2002
11:00am
149 Cullinane Hall
Northeastern University



ABSTRACT

The field of reinforcement learning (RL) has introduced into AI many
abstract mathematical formulations of the AI problem, mostly by borrowing
them from the fields of operations research and adaptive control. Has this
been good for AI? I will argue that RL formulations have allowed us to ask
and answer precise questions about many important AI issues as well as to
bring a (mostly) principled design methodology to many application areas. I
will illustrate these twin advantages through examples from my own work. In
the first part of the talk I will provide an answer to a formulation of the
“exploitation-exploration” tradeoff: should an agent exploit what it already
knows or should it explore in the hope of learning something that leads to
even greater long-term return? In the second part of the talk, I will
describe why and how RL offers a powerful methodology for designing many
human-computer interaction systems.  I will illustrate this methodology
through our design, construction and empirical evaluation of NJFun (a system
that provides telephonic access to a database of fun activities in NJ), and
show that RL measurably improves NJFun’s performance.

Host:
Ron Williams