Toward a Model of Intelligence as an Economy of Agents

  • Authors:
  • Eric B. Baum

  • Affiliations:
  • NEC Research Institute, 4 Independence Way, Princeton, NJ 08540. eric@research.nj.nec.com

  • Venue:
  • Machine Learning
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

A market-based algorithm is presented which autonomously apportionscomplex tasks to multiple cooperating agents giving each agent the motivation of improving performance of the whole system.A specific model, called “The Hayek Machine” is proposed and tested ona simulated Blocks World (BW) planning problem. Hayek learns to solvemore complex BW problems than any previous learning algorithm. Given intermediate reward and simple features, it has learned to efficiently solve arbitrary BWproblems. The Hayek Machine can also be seen as a model of evolutionary economics.