Skip navigation
Skip navigation

Feature Markov Decision Processes

Hutter, Marcus

Description

General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes (MDPs). So far it is

CollectionsANU Research Publications
Date published: 2009
Type: Conference paper
URI: http://hdl.handle.net/1885/58168
Source: Advances in Intelligent Systems Research: Proceedings of the 2nd Conference on Artificial General Intelligence (AGI 2009)
DOI: 10.2991/agi.2009.30

Download

File Description SizeFormat Image
01_Hutter_Feature_Markov_Decision_2009.pdf420.46 kBAdobe PDF    Request a copy
02_Hutter_Feature_Markov_Decision_2009.pdf37.49 kBAdobe PDF    Request a copy
03_Hutter_Feature_Markov_Decision_2009.pdf55.8 kBAdobe PDF    Request a copy
04_Hutter_Feature_Markov_Decision_2009.pdf55.32 kBAdobe PDF    Request a copy


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

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator