EP 4139849 A1 20230301 - METHOD FOR CONFIGURING COMPONENTS IN A SYSTEM BY MEANS OF MULTI-AGENT REINFORCEMENT LEARNING, COMPUTER-READABLE STORAGE MEDIUM, AND SYSTEM
Title (en)
METHOD FOR CONFIGURING COMPONENTS IN A SYSTEM BY MEANS OF MULTI-AGENT REINFORCEMENT LEARNING, COMPUTER-READABLE STORAGE MEDIUM, AND SYSTEM
Title (de)
VERFAHREN ZUM KONFIGURIEREN VON KOMPONENTEN IN EINEM SYSTEM MIT HILFE VON MULTI-AGENT REINFORCEMENT LEARNING, COMPUTERLESBARES SPEICHERMEDIUM UND SYSTEM
Title (fr)
PROCÉDÉ DE CONFIGURATION DE COMPOSANTS DANS UN SYSTÈME AU MOYEN D'UN APPRENTISSAGE PAR RENFORCEMENT MULTI-AGENT, SUPPORT DE STOCKAGE LISIBLE PAR ORDINATEUR ET SYSTÈME
Publication
Application
Priority
EP 2020065850 W 20200608
Abstract (en)
[origin: WO2021249616A1] Software systems consisting of a plurality of components often require said components to be configured so that said components can perform their task in an optimal manner for a particular application. The invention relates to a method for configuring a software system which consists of a plurality of components. To this end, two different alternatives are provided: a) mode 1, i.e. with offensive training, for quickly learning new situations: the range of values and the step size of the parameters are restricted to such an extent that only non-critical changes are possible with one action. Alternatively, b) mode 2 is used, i.e. defensive training, with continuous learning: the range of values and the step size of the parameters are restricted so that the changes do not significantly worsen the target variables; the Epsilon-Greedy value ε is set to a lower value.
IPC 8 full level
G06N 3/08 (2006.01)
CPC (source: EP US)
G05B 13/0265 (2013.01 - US); G05B 13/042 (2013.01 - US); G06N 3/088 (2013.01 - EP)
Citation (search report)
See references of WO 2021249616A1
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated extension state (EPC)
BA ME
Designated validation state (EPC)
KH MA MD TN
DOCDB simple family (publication)
WO 2021249616 A1 20211216; CN 115699030 A 20230203; EP 4139849 A1 20230301; US 2023259073 A1 20230817
DOCDB simple family (application)
EP 2020065850 W 20200608; CN 202080101841 A 20200608; EP 20735060 A 20200608; US 202018008578 A 20200608