Feature dynamic Bayesian networks

Date

Authors

Hutter, Marcus

Publisher

Atlantis Press

Abstract

Feature Markov Decision Processes (ΦMDPs) [Hut09] are well-suited for learning agents in general environments. Nevertheless, unstructured (Φ)MDPs are limited to relatively simple environments, Structured MDPs like Dynamic Bayesian Networks (DBNs) are us

Keywords

Keywords: Building blockes; Cost criteria; Dynamic Bayesian network; Dynamic bayesian networks; General learning; Learning agents; Markov Decision Processes; Primary contribution; Real-world problem; Distributed parameter networks; Feature extraction; Inference eng

URI

http://hdl.handle.net/1885/58189

Collections

ANU Research Publications

Source

Advances in Intelligent Systems Research: Proceedings of the 2nd Conference on Artificial General Intelligence (AGI 2009)

Type

Conference paper

DOI

10.2991/agi.2009.6

Restricted until

2037-12-31

Downloads

File

Description

01_Hutter_Feature_dynamic_Bayesian_2009.pdf (411.76 KB)

02_Hutter_Feature_dynamic_Bayesian_2009.pdf (36.89 KB)