Skip navigation
Skip navigation

Feature Dynamic Bayesian Networks

Hutter, Marcus

Description

Feature Markov Decision Processes (MDPs) [Hut09] are well-suited for learning agents in general environments. Nevertheless, unstructured ()MDPs are limited to rela- tively simple environments. Structured MDPs like Dynamic Bayesian Networks (DBNs) are used for large-scale real- world problems. In this article I extend MDP to DBN. The primary contribution is to derive a cost criterion that al- lows to automatically extract the most relevant features from the environment, leading to the "best" DBN...[Show more]

CollectionsANU Research Publications
Date published: 2009-05
Type: Conference paper
URI: http://hdl.handle.net/1885/14961
DOI: 10.2991/agi.2009.6

Download

File Description SizeFormat Image
Hutter Feature Dynamic 2009.pdf411.76 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator