** Next:** INTRODUCTION
**Up:** Quasi-Bayesian home page

#
Quasi-Bayesian Strategies for Efficient Plan Generation:
Application to the *Planning to Observe* Problem

**
Fabio Cozman
Eric Krotkov **

fgcozman@cs.cmu.edu

Robotics Institute,
School of Computer Science,
Carnegie Mellon University

Pittsburgh, PA

### Abstract:

Quasi-Bayesian
theory uses convex sets of probability distributions
and expected loss to represent preferences about plans. The theory focuses
on decision *robustness*,
i.e., the extent to which plans are affected by
deviations in subjective assessments of probability.
The present work presents solutions for
plan generation when robustness of probability assessments must be
included: plans contain information about the robustness of certain actions.
The surprising result is that some
problems can be solved faster in the
Quasi-Bayesian
framework than
within usual Bayesian theory. We investigate this on the *planning to
observe* problem, i.e., an agent must decide whether to take new
observations or not. The fundamental question is: How, and how much, to
search for a ``best'' plan, based on the robustness of probability assessments?
Plan generation algorithms are derived in the context of material
classification with an acoustic robotic probe. A package that constructs
Quasi-Bayesian plans is available through
anonymous ftp.

### Directions for the reader:

These pages contain the main points of the original paper, presented
at the
Twelfth Conference
on Uncertainty in Artificial Intelligence,
August 1-3, 1996, Reed College Portland, Oregon, USA; the conference
is organized by the Association for
Uncertainty in Artificial Intelligence.
The original paper contains mathematical expressions that are not easily
translated to HTML; the sections that use too many mathematics were
greatly reduced and summarized. For a complete version of the paper,
the compressed postscript version is indicated.

These pages were generated from a LaTeX original through the
LaTeX2HTML program. The conversion was configured so that HTML 3.0
math symbols were generated; even if your browser does not support such
mathematical markup, it should be (relatively) easy to read the expressions.

© Fabio Cozman[Send Mail?]

Sun Jul 14 18:32:36 EDT 1996