Patent · US Active

Controller optimization via reinforcement learning on asset avatar

US11674384B2 · kind B2 · utility

0Cited by
16References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 20, 2020
Grant dateJun 13, 2023
Priority date
Expiry dateMay 27, 2041

Classification

  • Technology area (CPC E)Fixed Constructions
  • CPC primaryE21B2200/22
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method can include receiving sensor data from a system; encoding the sensor data to a latent space representation via a trained encoder; generating a control action using the latent space representation; and issuing an instruction that corresponds to the control action for control of the system.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.