Patent · US Active

Vehicle controller, vehicle control system, vehicle learning device, vehicle learning method, and memory medium

US11377084B2 · kind B2 · utility

1Cited by
2References
9Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 6, 2020
Grant dateJul 5, 2022
Priority date
Expiry dateJan 12, 2041

Classification

  • Technology area (CPC F)Mechanical Engineering; Lighting; Heating
  • CPC primaryF02D2200/50
  • WIPO fieldTransport
  • WIPO sectorMechanical engineering

Abstract

An update process updates relationship defining data by inputting, to a predetermined update map, a state of a vehicle obtained by a state obtaining process, a value of an action variable used to operate an electronic device, and a reward corresponding to an operation of an electronic device. A range in which an operation process uses, as the action variable, a value different from a value that maximizes an expected return related to the reward is defined as a return non-maximizing range. In a case in which a degree of deterioration of the vehicle is greater than or equal to a predetermined degree, a changing process changes the return non-maximizing range to a side on which the return non-maximizing range is expanded as compared to a case in which the degree of deterioration is less than the predetermined degree.

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