Method, device and computer programm for producing a strategy for a robot

verfasst von

Frank Hutter, Lior Fuks, Marius Lindauer, Noor Awad

Abstract

A method for producing a strategy for a robot. The method includes the following steps: initializing the strategy and an episode length; repeated execution of the loop including the following steps: producing a plurality of further strategies as a function of the strategy; applying the plurality of the further strategies for the length of the episode length; ascertaining respectively a cumulative reward, which is obtained in the application of the respective further strategy; updating the strategy as a function of a second plurality of the further strategies that obtained the greatest cumulative rewards. After each execution of the loop, the episode length is increased. A computer program, a device for carrying out the method, and a machine-readable memory element on which the computer program is stored, are also described.

Organisationseinheit(en)

Fachgebiet Maschinelles Lernen

Externe Organisation(en)

Robert Bosch GmbH

Typ

Patent

Publikationsdatum

14.01.2021

Publikationsstatus

Veröffentlicht

Elektronische Version(en)

https://at.espacenet.com/publicationDetails/biblio?FT=D&date=20210114&DB=EPODOC&locale=de_AT&CC=US&NR=2021008718A1&KC=A1&ND=4 (Zugang: Offen)
https://at.espacenet.com/publicationDetails/biblio?FT=D&date=20210112&DB=EPODOC&locale=de_AT&CC=CN&NR=112215363A&KC=A&ND=5 (Zugang: Offen)
https://at.espacenet.com/publicationDetails/biblio?FT=D&date=20210114&DB=EPODOC&locale=de_AT&CC=DE&NR=102019210372A1&KC=A1&ND=5 (Zugang: Offen)