Publication - Learning Experiments in a Heterogeneous Multi-agent System

Authors: Prasad, Nagendra, Lesser, Victor, and Lander, Susan
Title: Learning Experiments in a Heterogeneous Multi-agent System
Abstract: Self-organization for efficient distributed search control has received much attention previously but the work presented in this paper represents one of the few attempts at demonstrating its viability and utility in an agent-based system involving complex interactions within the agent set. We discuss experiments with a heterogeneous multi-agent parametric design system called L-TEAM where machine learning techniques endow the agents with capabilities to learn their organizational roles in negotiated search and to learn meta-level knowledge about the composite search spaces. We tested the system on a steam condenser design domain and empirically demonstrated its usefulness.
Keywords: Learning, Multi-Agent Systems
Publication: IJCAI-95 Workshop on Adaptation and Learning in Multiagent Systems
Location: Montreal, Canada
Date: January 1995
Sources: PS: /Documents/nagendra_IJCAI95.ps
PDF: /Documents/lesser/nagendra_IJCAI95.pdf
Reference: Prasad, Nagendra, Lesser, Victor, and Lander, Susan. Learning Experiments in a Heterogeneous Multi-agent System. IJCAI-95 Workshop on Adaptation and Learning in Multiagent Systems. January 1995.
bibtex:
@article{Prasad-141,
  author    = "Nagendra Prasad and Victor Lesser and Susan Lander",
  title     = "{Learning Experiments in a Heterogeneous
               Multi-agent System}",
  journal   = "IJCAI-95 Workshop on Adaptation and Learning in
               Multiagent Systems",
  month     = "January",
  year      = "1995",
  address   = "Montreal, Canada",
  url       = "http://mas.cs.umass.edu/paper/141",
}