Fully probabilistic design of strategies with estimator

Kód výsledku v IS VaVaI

RIV/67985556:_____/22:00556428 - isvavai.cz

Výsledek na webu

https://www.sciencedirect.com/science/article/pii/S0005109822001145?via%3Dihub

DOI - Digital Object Identifier

10.1016/j.automatica.2022.110269

Jazyk výsledku

angličtina

Název v původním jazyce

Fully probabilistic design of strategies with estimator

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Fully probabilistic design of strategies with estimator

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

LTC18075: Distribuované racionální rozhodování: kooperační aspekty

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Automatica

ISSN

0005-1098

e-ISSN

1873-2836

Svazek periodika

141

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

6

Strana od-do

110269

Kód UT WoS článku

000797650300001

EID výsledku v databázi Scopus

2-s2.0-85127517743