Patent · US Active

Interpretability of deep reinforcement learning models in assistant systems

US11715042B1 · kind B1 · utility

14Cited by
142References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 19, 2019
Grant dateAug 1, 2023
Priority date
Expiry dateSep 10, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In one embodiment, a method includes training a target machine-learning model iteratively by accessing training data of content objects, training an intermediate machine-learning model that outputs contextual evaluation measurements based on the training data, generating state-indications associated with the training data, wherein the state-indications comprise user-intents, system actions, and user actions, training the target machine-learning model based on the contextual evaluation measurements, the state-indications, and an action set comprising possible system actions, extracting rules based on the target machine-learning model by a sequential pattern-mining model, generating synthetic training data based on the rules, updating the training data by adding the synthetic training data to the training data, determining if a completion condition is reached for the training, and if the completion condition is reached returning the target machine-learning model, else repeating the iterative training of the target machine-learning model.

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