Dynamic Programming for Partially Observable Stochastic Games

DMCA

Dynamic Programming for Partially Observable Stochastic Games (2004)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Eric A. Hansen

Venue:	IN PROCEEDINGS OF THE NINETEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE
Citations:	159 - 25 self

BibTeX

@INPROCEEDINGS{Hansen04dynamicprogramming,
    author = {Eric A. Hansen},
    title = {Dynamic Programming for Partially Observable Stochastic Games},
    booktitle = {IN PROCEEDINGS OF THE NINETEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE},
    year = {2004},
    pages = {709--715},
    publisher = {}
}

OpenURL

Abstract

We develop an exact dynamic programming algorithm for partially observable stochastic games (POSGs). The algorithm is a synthesis of dynamic programming for partially observable Markov decision processes (POMDPs) and iterated elimination of dominated strategies in normal form games.

Keyphrases

dynamic programming partially observable stochastic game observable markov decision process iterated elimination normal form game exact dynamic programming algorithm dominated strategy observable stochastic game

DMCA