Patent · US Active

Meta-agent for reinforcement learning

US12387138B2 · kind B2 · utility

0Cited by
3References
14Claims
0Family size

Assignee

Inventor

Key dates

Filing dateJun 14, 2022
Grant dateAug 12, 2025
Priority date
Expiry dateApr 2, 2044

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/20
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A computing machine receives a request for an action by a meta-agent at the computing machine. The computing machine selects, using the meta-agent, an agent for determining an action responsive to the request. The agent is selected from a plurality of reinforcement learning agents. The agent is selected based on values in a dataset associated with the request. At least a portion of the dataset has predefined value types. The meta-agent and each agent from the plurality of reinforcement learning agents is trained using datasets including the predefined value types. The computing machine transmits, to the selected agent, the request for the action to cause the agent to compute the action.

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