Global Patent Index - EP 3884432 A1

EP 3884432 A1 20210929 - REINFORCEMENT LEARNING MODEL TRAINING THROUGH SIMULATION

Title (en)

REINFORCEMENT LEARNING MODEL TRAINING THROUGH SIMULATION

Title (de)

TRAINING EINES VERSTÄRKUNGSLERNMODELLS DURCH SIMULATION

Title (fr)

APPRENTISSAGE DE MODÈLE D'APPRENTISSAGE DE RENFORT PAR SIMULATION

Publication

EP 3884432 A1 20210929 (EN)

Application

EP 19829363 A 20191120

Priority

  • US 201816198605 A 20181121
  • US 201816198698 A 20181121
  • US 201816201830 A 20181127
  • US 201816201864 A 20181127
  • US 201816201872 A 20181127
  • US 2019062509 W 20191120

Abstract (en)

[origin: WO2020106908A1] A simulation management service receives a request to perform reinforcement learning for a robotic device. The request can include computer-executable code defining a reinforcement function for training a reinforcement learning model for the robotic device. In response to the request, the simulation management service generates a simulation environment and injects the computer-executable code into a simulation application for the robotic device. Using the simulation application and the computer-executable code, the simulation management service performs the reinforcement learning within the simulation environment.

IPC 8 full level

G06N 3/00 (2006.01); G06N 20/00 (2019.01)

CPC (source: EP)

G06N 3/006 (2013.01); G06N 20/00 (2018.12)

Citation (search report)

See references of WO 2020106908A1

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

DOCDB simple family (publication)

WO 2020106908 A1 20200528; CN 113272825 A 20210817; CN 113272825 B 20240202; EP 3884432 A1 20210929

DOCDB simple family (application)

US 2019062509 W 20191120; CN 201980086986 A 20191120; EP 19829363 A 20191120