BIOGRAPHY
In recent years, certain interests within the multi-agent systems and machine learning communities have merged to create a new field of wide interest: multi-agent learning. Research in this area is concerned with learning not in the classic case of an agent and its environment, but rather with interactive learning among multiple agents. My research focuses on multi-agent learning among Internet agents engaged in game-theoretic (i.e., strategic) activities, such as bidding in on-line auctions and dynamic pricing among shopbots and pricebots.
Specifically, my research goals include the following: (i) the design of learning algorithms that behave near-optimally in the non-stationary environments that naturally arise in Internet settings, (ii) the design of new game-theoretic solution concepts capable of modeling the collective behavior of adaptive, Internet agents that employ strategies of the form described in (i), and (iii) the design of market mechanisms capable of inducing collective Internet behavior that satisfies globally desirable properties such as stability, fairness, and efficiency.
I received my Ph.D. in 1999 from the Courant Institute of Mathematical Sciences at New York University. Prior to my position at Brown, I was employed by the Institute for Advanced Commerce at IBM's T.J. Watson Research Center. I live in Boston, where I enjoy tennis, yoga, and art museums.
|
