Decision-Theoretic Planning: Structural Assumptions and Computational Leverage

DMCA

Decision-Theoretic Planning: Structural Assumptions and Computational Leverage (1999)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Craig Boutilier , Thomas Dean , Steve Hanks

Venue:	JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH
Citations:	508 - 4 self

BibTeX

@ARTICLE{Boutilier99decision-theoreticplanning:,
    author = {Craig Boutilier and Thomas Dean and Steve Hanks},
    title = {Decision-Theoretic Planning: Structural Assumptions and Computational Leverage},
    journal = {JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH},
    year = {1999},
    volume = {11},
    pages = {1--94}
}

OpenURL

Abstract

Planning under uncertainty is a central problem in the study of automated sequential decision making, and has been addressed by researchers in many different fields, including AI planning, decision analysis, operations research, control theory and economics. While the assumptions and perspectives adopted in these areas often differ in substantial ways, many planning problems of interest to researchers in these fields can be modeled as Markov decision processes (MDPs) and analyzed using the techniques of decision theory. This paper presents an overview and synthesis of MDP-related methods, showing how they provide a unifying framework for modeling many classes of planning problems studied in AI. It also describes structural properties of MDPs that, when exhibited by particular classes of problems, can be exploited in the construction of optimal or approximately optimal policies or plans. Planning problems commonly possess structure in the reward and value functions used to de...

Keyphrases

structural assumption decision-theoretic planning computational leverage central problem structural property particular class decision analysis unifying framework ai planning substantial way optimal policy many class mdp-related method many different field decision theory control theory operation research sequential decision making markov decision process value function

DMCA