Discounted fully probabilistic design of decision rules

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F24%3A00599786" target="_blank" >RIV/67985556:_____/24:00599786 - isvavai.cz</a>

Result on the web

<a href="https://www.sciencedirect.com/science/article/pii/S0020025524014920?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0020025524014920?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.ins.2024.121578" target="_blank" >10.1016/j.ins.2024.121578</a>

Result language

angličtina

Original language name

Discounted fully probabilistic design of decision rules

Original language description

Axiomatic fully probabilistic design (FPD) of optimal decision rules strictly extends the decision making (DM) theory represented by Markov decision processes (MDP). This means that any MDP task can be approximated by an explicitly found FPD task whereas many FPD tasks have no MDP equivalent. MDP and FPD model the closed loop — the coupling of an agent and its environment — via a joint probability density (pd) relating the involved random variables, referred to as behaviour. Unlike MDP, FPD quantifies agent’s aims and constraints by an ideal pd. The ideal pd is high on the desired behaviours, small on undesired behaviours and zero on forbidden ones. FPD selects the optimal decision rules as the minimiser of Kullback-Leibler’s divergence of the closed-loop-modelling pd to its ideal twin. The proximity measure choice follows from the FPD axiomatics. MDP minimises the expected total loss, which is usually the sum of discounted partial losses. The discounting reflects the decreasing importance of future losses. It also diminishes the influence of errors caused by:n▶ the imperfection of the employed environment model.n▶ roughly-expressed aims.n▶ the approximate learning and decision-rules design.nThe established FPD cannot currently account for these important features. The paper elaborates the missing discounted version of FPD. This non-trivial filling of the gap in FPD also employs an extension of dynamic programming, which is of an independent interest.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

20204 - Robotics and automatic control

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2024

Confidentiality

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

Name of the periodical

Information Sciences

ISSN

0020-0255

e-ISSN

1872-6291

Volume of the periodical

690

Issue of the periodical within the volume

1

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

12

Pages from-to

121578

UT code for WoS article

001369164400001

EID of the result in the Scopus database

2-s2.0-85207087101