Recent Progress in Co-evolutionary
Computing
Dr. Jordan Pollack
Department of Computer Science
Date: Monday November 13, 2006
Time: 12:15 p.m. - 1:10 p.m.
Location: 101 Perkins
Abstract
For many years
my lab has been working on electronic and software systems which can learn and
develop on their own in openended innovative ways.
This is based on understanding and mimicking natural coevolution.
However, in nature, coevolution refers to the
contingent development between species. For machine learning, coevolution has come to mean the search for “arms-race”
type phenomena which can lead multiple agents to develop through their own
interaction, without the need for an intelligent designer. The setup is usually
as a set of players to a “game” who start with only the rules and must develop
strategy or tactics through interaction. Generally, this interaction is a
two-level competition - first in playing a game, and second in competing for
limited slots in a fixed-size population. We have had some success, for example
in optimization, such as discovering the best sorting networks and cellular
automata rules, as well as in three generations of automatically designed
robots. However, as we developed these co-evolutionary learning algorithms, we
found many phenomena which arise to prevent continuous innovation. These
phenomena are economic rather than biologic, and include winner-take-all
monopolies, boom/bust cycles, and stable mediocre oligarchies (groups of
players who tacitly collude to protect each other from further innovation.) We
have been developing new techniques for avoiding these problems in
co-evolution, including Pareto coevolution, emergent dimensions,
and memory mechanisms. We have developed a new principle to understand learning
among agents - “The Teacher’s Dilemma,” which models the teacher-student
relationship, and provides a new interaction framework which is neither
competitive nor altruistic. The first major practical application of this work
has been the development of scaleable peer-to-peer learning environments for children.
These are multi-player online video games, but the highest scores accrue to
players who provide appropriate challenges to each other, essentially turning students
into each other’s teachers. We launched the first online spelling bee in 2004
and now have 40,000 members in www.Beeweb.org.
Jordan B.
Pollack received the Ph.D from
Sponsoring
Organizations:
Computer Science
Student Association •