Value-Driven Information Gathering

Joshua Grass and Shlomo Zilberstein. Value-Driven Information Gathering. Proceedings of the AAAI Workshop on Building Resource-Bounded Reasoning Systems, Providence, Rhode Island, 1997.

Abstract

We describe a decision-theoretic approach to information gathering from a distributed network of information sources. Our approach uses an explicit representation of the user's decision model in order to plan and executein formation gathering actions. The information gathering planner issues requests based on the value of information taking in to account the computational resources and monetary costs of information gathering. At any given time, the system assesses the marginal value of dispatching new queries and selects the one with maximal value. When no further improvement of the comprehensive utility function is possible, the system stops gathering information and reports the results. We show that this approach has significant advantages including high performance, interruptibility, and adaptability to dynamic changes in the environment.

Bibtex entry:

@inproceedings{GZaaai97ws,
  author	= {Joshua Grass and Shlomo Zilberstein},
  title		= {Value-Driven Information Gathering},
  booktitle     = {Proceedings of the AAAI Workshop on Building Resource-Bounded
                   Reasoning Systems},
  year		= {1997},
  pages		= {},
  address       = {Providence, Rhode Island},
  url		= {http://rbr.cs.umass.edu/shlomo/papers/GZaaai97ws.html}
}

shlomo@cs.umass.edu
UMass Amherst