Number of the records: 1
Fully probabilistic design of strategies with estimator
- 1.
SYSNO ASEP 0556428 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Fully probabilistic design of strategies with estimator Author(s) Kárný, Miroslav (UTIA-B) RID, ORCID Number of authors 1 Article number 110269 Source Title Automatica. - : Elsevier - ISSN 0005-1098
Roč. 141, č. 1 (2022)Number of pages 6 s. Publication form Print - P Language eng - English Country NL - Netherlands Keywords Bayes methods ; closed loop systems ; decision making ; dynamic programming ; estimation Subject RIV BB - Applied Statistics, Operational Research OECD category Robotics and automatic control R&D Projects LTC18075 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) Method of publishing Limited access Institutional support UTIA-B - RVO:67985556 UT WOS 000797650300001 EID SCOPUS 85127517743 DOI 10.1016/j.automatica.2022.110269 Annotation 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. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2023 Electronic address https://www.sciencedirect.com/science/article/pii/S0005109822001145?via%3Dihub
Number of the records: 1