FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision Problems

FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision Problems

Show other versions (1)

Finding optimal solutions to Partially Observable Markov Decision Problems is known to be NP-hard. This paper describes a novel neuro-fuzzy approach to obtain fast, robust and easily interpreted solutions by utilizing a combination of several learning techniques including neural networks, fuzzy deci...

Full description

Bibliographic Details
Main Authors: Levent Akin, Toygar Karadeniz
Format: Article
Language:English
Published: SAGE Publishing 2008-11-01
Series:International Journal of Advanced Robotic Systems
Subjects:
POMDP
neuro-fuuzy
rule-based systems
Online Access:http://www.intechopen.com/articles/show/title/fdms_with_q-learning__a_neuro-fuzzy_approach_to_partially_observable_markov_decision_problems
id doaj-bf18bd74e45a4d92b8c5c14fd13a65ff
record_format Article
spelling doaj-bf18bd74e45a4d92b8c5c14fd13a65ff2020-11-25T03:43:17ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88061729-88142008-11-0114FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision ProblemsLevent AkinToygar KaradenizFinding optimal solutions to Partially Observable Markov Decision Problems is known to be NP-hard. This paper describes a novel neuro-fuzzy approach to obtain fast, robust and easily interpreted solutions by utilizing a combination of several learning techniques including neural networks, fuzzy decision making and Q-learning. http://www.intechopen.com/articles/show/title/fdms_with_q-learning__a_neuro-fuzzy_approach_to_partially_observable_markov_decision_problemsPOMDPneuro-fuuzyrule-based systems
collection DOAJ
language English
format Article
sources DOAJ
author Levent Akin
Toygar Karadeniz
spellingShingle Levent Akin
Toygar Karadeniz
FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision Problems
International Journal of Advanced Robotic Systems
POMDP
neuro-fuuzy
rule-based systems
author_facet Levent Akin
Toygar Karadeniz
author_sort Levent Akin
title FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision Problems
title_short FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision Problems
title_full FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision Problems
title_fullStr FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision Problems
title_full_unstemmed FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision Problems
title_sort fdms with q-learning: a neuro-fuzzy approach to partially observable markov decision problems
publisher SAGE Publishing
series International Journal of Advanced Robotic Systems
issn 1729-8806
1729-8814
publishDate 2008-11-01
description Finding optimal solutions to Partially Observable Markov Decision Problems is known to be NP-hard. This paper describes a novel neuro-fuzzy approach to obtain fast, robust and easily interpreted solutions by utilizing a combination of several learning techniques including neural networks, fuzzy decision making and Q-learning.
topic POMDP
neuro-fuuzy
rule-based systems
url http://www.intechopen.com/articles/show/title/fdms_with_q-learning__a_neuro-fuzzy_approach_to_partially_observable_markov_decision_problems
work_keys_str_mv AT leventakin fdmswithqlearninganeurofuzzyapproachtopartiallyobservablemarkovdecisionproblems
AT toygarkaradeniz fdmswithqlearninganeurofuzzyapproachtopartiallyobservablemarkovdecisionproblems
_version_ 1724520968069578752

Similar Items