Patent · US Active

Reinforcement learning using target neural networks

US11049008B2 · kind B2 · utility

7Cited by
2References
29Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 9, 2017
Grant dateJun 29, 2021
Priority date
Expiry dateDec 27, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

We describe a method of reinforcement learning for a subject system having multiple states and actions to move from one state to the next. Training data is generated by operating on the system with a succession of actions and used to train a second neural network. Target values for training the second neural network are derived from a first neural network which is generated by copying weights of the second neural network at intervals.

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