Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
Sound Abstraction of Probabilistic Actions in The Constraint Mass Assignment Framework
AnHai Doan, Peter Haddawy
Abstract:
This paper provides a formal and practical framework for sound abstraction of probabilistic actions. We start by precisely defining the concept of sound abstraction within the context of finite-horizon planning (where each plan is a finite sequence of actions). Next we show that such abstraction cannot be performed within the traditional probabilistic action representation, which models a world with a single probability distribution over the state space. We then present the constraint mass assignment representation, which models the world with a set of probability distributions and is a generalization of mass assignment representations. Within this framework, we present sound abstraction procedures for three types of action abstraction. We end the paper with discussions and related work on sound and approximate abstraction. We give pointers to papers in which we discuss other sound abstraction-related issues, including applications, estimating loss due to abstraction, and automatically generating abstraction hierarchies.
Keywords: Abstraction, probabilistic planning, decision-theoretic planning.
Pages: 228-235
PS Link: ftp://ftp.cs.uwm.edu/pub/tech_reports/ai/doan-aips96.ps.Z
PDF Link: /papers/96/p228-doan.pdf
BibTex:
@INPROCEEDINGS{Doan96,
AUTHOR = "AnHai Doan and Peter Haddawy",
TITLE = "Sound Abstraction of Probabilistic Actions in The Constraint Mass Assignment Framework",
BOOKTITLE = "Proceedings of the Twelfth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-96)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "1996",
PAGES = "228--235"
}


hosted by DSL   •   site info   •   help