Patent · US Active

Reinforcement and imitation learning for a task

US12343874B2 · kind B2 · utility

0Cited by
3References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 25, 2023
Grant dateJul 1, 2025
Priority date
Expiry dateJan 8, 2044

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/098
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.

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