Patent · US Active

Weakly supervised reinforcement learning

US11809977B2 · kind B2 · utility

0Cited by

1References

21Claims

0Family size

Assignee

NEC Laboratories Europe GmbH · DE

Inventors

Mauricio Fadel Argerich · Heidelberg, DE
Jonathan Fuerst · Heidelberg, DE
Bin Cheng · Sandhausen, DE

Key dates

Filing date	Feb 10, 2020
Grant date	Nov 7, 2023
Priority date	—
Expiry date	Apr 20, 2042

Classification

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

Abstract

A method for reinforcement machine learning uses a reinforcement learning system that has an environment and an agent. The agent has a policy providing a mapping between states of the environment and actions. The method includes: determining a current state of the environment; determining, using the policy, a current policy output based on the current state; determining, using a knowledge function, a current knowledge function output based on the current state; determining an action based on the current policy output and the current knowledge function output; applying the action to the environment resulting in updating the current state and determining a reward; and updating the policy based on at least one of the current state and the reward.

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