Acting and Bayesian reinforcement structure learning of partilally observable environment
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F14%3A10286585" target="_blank" >RIV/00216208:11320/14:10286585 - isvavai.cz</a>
Result on the web
<a href="http://ceur-ws.org/Vol-1214/21.pdf" target="_blank" >http://ceur-ws.org/Vol-1214/21.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Acting and Bayesian reinforcement structure learning of partilally observable environment
Original language description
This article shows how to learn both the structure and the parameters of partially observable environment simultaneously while also online performing near-optimal sequence of actions taking into account exploration-exploitation tradeoff. It combines tworesults of recent research: The former extends model-based Bayesian reinforcement learning of fully observable environment to bigger domains by learning the structure. The latter shows how a known structure can be exploited to model-based Bayesian reinforcement learning of partially observable domains. This article shows that merging both approaches is possible without too excessive increase in computational complexity.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GAP202%2F10%2F1333" target="_blank" >GAP202/10/1333: NoSCoM: Non-Standard Computational Models and Their Applications in Complexity, Linguistics, and Learning</a><br>
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 14th conference Information Technologies - Applications and Theory (ITAT 2014) - Workshops and Posters
ISBN
978-80-87136-19-5
ISSN
1613-0073
e-ISSN
—
Number of pages
7
Pages from-to
21-27
Publisher name
Ústav informatiky AV ČR
Place of publication
Praha, Česká republika
Event location
Demänovská Dolina, Slovakia
Event date
Sep 25, 2014
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—