Haiyan Qiao
Department of Electrical and Computer Engineering
The University of Arizona
April 16, 2007 11:00 a.m. to 12:00 p.m.  JB 389/391

Title: Multiagent Learning Methods and Applications


Abstract: Learning in the natural world occurs when an agent, which 
perceives its current state and takes actions, interacts with the 
environment, which in return provides a positive or negative feedback. 
Research of reinforcement learning studies such processes and attempts to 
find policies that map states of the world to the actions the agent ought 
to take in those states for maximizing cumulative reward for the agent over
the long run. In multi-agent systems, agent learning becomes more 
challenging, since the optimal action of each agent generally depends upon
the actions of other agents. This talk provides an introduction to the 
problems in multiagent learning.  The framework and basic concepts in 
multiagent reinforcement learning will be covered, followed by a brief 
introduction to a variety of approaches currently being studied by 
researchers. Most existing multiagent learning research focuses on 
non-cooperative games where equilibrium is a learning objective. However, 
in many situations, the agents may seek to cooperate with each other to 
reach a win-win situation. I will introduce a novel multiagent learning 
model with bargaining that is well suited to cooperative games, and present
some experimental results. The approach will be illustrated by applying it
to agent economics. If time permits, its applications in engineering will 
also be discussed.