Patent · US Active

Training a character through interactions

US12056581B1 · kind B1 · utility

0Cited by
3References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 10, 2020
Grant dateAug 6, 2024
Priority date
Expiry dateOct 5, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N7/01
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Various implementations disclosed herein include devices, systems, and methods for training of an action determining component of a computer character. In some implementations, actions are taken by the character in a 3D environment according to an action determining component of the character, where the character is rewarded or penalized for interactions associated with an object/concept in the 3D environment according to an assigned object/concept reward or penalty. In some implementations, the reward or the penalty assigned to the object/concept is modified, and the character is then rewarded or penalized for interactions associated with the object/concept according to the modified reward or the modified penalty. The action determining component of the character is trained using a reinforcement learning technique that accounts for rewards or penalties obtained by virtual character for interactions associated with the object/concept.

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