Solving in an efficient manner many different optimal control tasks within the same underlying environment requires decomposing the environment into its computationally elemental ...
Imitation is actively being studied as an effective means of learning in multi-agent environments. It allows an agent to learn how to act well (perhaps optimally) by passively obs...
In recent years, with the rapid proliferation of digital images, the need to search and retrieve the images accurately, efficiently, and conveniently is becoming more acute. Automa...
In this paper, we describe the lessons we learned in developing AgentBuilder, a commercial system for rapidly creating agents that extract information from web sites. AgentBuilder...
We present a classification algorithm built on our adaptation of the Generalized Lotka-Volterra model, well-known in mathematical ecology. The training algorithm itself consists ...
Karen Hovsepian, Peter Anselmo, Subhasish Mazumdar