Planning and acting in partially observable stochastic domains

DMCA

Planning and acting in partially observable stochastic domains (1998)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Leslie Pack Kaelbling , Michael L. Littman , Anthony R. Cassandra

Venue:	ARTIFICIAL INTELLIGENCE
Citations:	1076 - 38 self

BibTeX

@ARTICLE{Kaelbling98planningand,
    author = {Leslie Pack Kaelbling and Michael L. Littman and Anthony R. Cassandra},
    title = {Planning and acting in partially observable stochastic domains},
    journal = {ARTIFICIAL INTELLIGENCE},
    year = {1998},
    volume = {101},
    pages = {99--134}
}

OpenURL

Abstract

In this paper, we bring techniques from operations research to bear on the problem of choosing optimal actions in partially observable stochastic domains. We begin by introducing the theory of Markov decision processes (mdps) and partially observable mdps (pomdps). We then outline a novel algorithm for solving pomdps offline and show how, in some cases, a finite-memory controller can be extracted from the solution to a pomdp. We conclude with a discussion of how our approach relates to previous work, the complexity of finding exact solutions to pomdps, and of some possibilities for finding approximate solutions.

Keyphrases

observable stochastic domain optimal action pomdps offline approximate solution observable mdps exact solution previous work operation research novel algorithm markov decision process finite-memory controller

DMCA