Publication - Cooperative Learning over Composite Search Spaces: Experiences with a Multi-agent Design System

Authors: Nagendra, Prasad, M.V., Lander, S.E, Lesser, V.R.
Title: Cooperative Learning over Composite Search Spaces: Experiences with a Multi-agent Design System
Abstract: We suggest the use of two learning techniques - short term and long term - to enhance search efficiency in a multi-agent design system by letting the agents learn about non-local requirements on the local search process. The first technique allows an agent to ac- cumulate and apply constraining information about global problem solving, gathered as a result of agent communication, to further problem solving within the same problem instance. The second technique is used to classify problem instances and appropriately in- dex and retrieve constraining information to apply to new problem instances. These techniques will be pre- sented within the context of a multi-agent parametric- design application called STEAM. We show that learning conclusively improves solution quality and processing- time results.
Keywords: Distributed Search, Learning, Multi-Agent Systems
Publication: Proceedings of the Thirteenth National Conference on Artificial Intelligence, Vol: 1, pp. 68 - 73
Location: Portland, Oregon
Publisher: AAAI Presss / MIT Press
Date: January 1996
Sources: PDF: /Documents/lesser/AAAI_96.pdf
Reference: Nagendra, Prasad, M.V., Lander, S.E, Lesser, V.R.. Cooperative Learning over Composite Search Spaces: Experiences with a Multi-agent Design System. Proceedings of the Thirteenth National Conference on Artificial Intelligence, Volume 1, AAAI Presss / MIT Press, pp. 68-73. January 1996.
bibtex: 
@article{Nagendra-101,
  author    = "Prasad Nagendra and Lander M.V. and Lesser S.E and
               V.R.",
  title     = "{Cooperative Learning over Composite Search Spaces:
               Experiences with a Multi-agent Design System}",
  journal   = "Proceedings of the Thirteenth National Conference
               on Artificial Intelligence",
  volume    = "1",
  publisher = "AAAI Presss / MIT Press",
  pages     = "68-73",
  month     = "January",
  year      = "1996",
  address   = "Portland, Oregon",
  url       = "http://mas.cs.umass.edu/paper/101",
}