Interpretability of deep reinforcement learning models in assistant systems
US11715042B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 19, 2019 |
| Grant date | Aug 1, 2023 |
| Priority date | — |
| Expiry date | Sep 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.