bibtype	J - Journal Article
ARLID	0556428
utime	20250310142432.1
mtime	20220406235959.9
SCOPUS	85127517743
WOS	000797650300001
DOI	10.1016/j.automatica.2022.110269
title (primary) (eng)	Fully probabilistic design of strategies with estimator
specification	page_count 6 s. media_type P
serial	ARLID cav_un_epca*0256218 ISSN 0005-1098 title Automatica volume_id 141 publisher name Elsevier
keyword	Bayes methods
keyword	closed loop systems
keyword	decision making
keyword	dynamic programming
keyword	estimation
author (primary)	ARLID cav_un_auth*0101124 name1 Kárný name2 Miroslav institution UTIA-B full_dept (cz) Adaptivní systémy full_dept (eng) Department of Adaptive Systems department (cz) AS department (eng) AS full_dept Department of Adaptive Systems fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source	url http://library.utia.cas.cz/separaty/2022/AS/karny-0556428.pdf
source	url https://www.sciencedirect.com/science/article/pii/S0005109822001145?via%3Dihub
cas_special	project project_id LTC18075 agency GA MŠk country CZ ARLID cav_un_auth*0372050 abstract (eng) The axiomatic fully probabilistic design (FDP) of decision strategies strictly extends Bayesian decision making (DM) theory. FPD also models the closed decision loop by a joint probability density (pd) of all inspected random variables, referred as behaviour. FPD expresses DM aims via an ideal pd of behaviours, unlike the usual DM. Its optimal strategy minimises Kullback–Leibler divergence (KLD) of the joint, strategy-dependent, pd of behaviours to its ideal twin. A range of FPD results confirmed its theoretical and practical strength. Curiously, no guide exists how to select a specific ideal pd for an estimator design. The paper offers it. It advocates the use of the closed-loop state notion and generalises dynamic programming so that FPD is its special case. Primarily, it provides an explorative optimised feedback that ‘‘naturally’’ diminishes exploration (gained in learning) as the learning progresses. result_subspec WOS RIV BB FORD0 20000 FORD1 20200 FORD2 20204 reportyear 2023 num_of_auth 1 mrcbC52 4 A sml 4as 2rh 20231122150503.7 2 R hod 20250310142401.4 20250310142432.1 inst_support RVO:67985556 permalink http://hdl.handle.net/11104/0330841 mrcbC61 1 confidential S contract name Publishing Agreement date 20220315 article_num 110269 mrcbC86 3+4 Article Automation Control Systems|Engineering Electrical Electronic mrcbC91 C mrcbT16-e AUTOMATIONCONTROLSYSTEMS|ENGINEERINGELECTRICALELECTRONIC mrcbT16-j 2.494 mrcbT16-s 3.657 mrcbT16-D Q1* mrcbT16-E Q1* arlyear 2022 mrcbTft \nSoubory v repozitáři: karny-556428.pdf, karny-0556428-AUT110269.html mrcbU14 85127517743 SCOPUS mrcbU24 PUBMED mrcbU34 000797650300001 WOS mrcbU63 cav_un_epca*0256218 Automatica 0005-1098 1873-2836 Roč. 141 č. 1 2022 Elsevier