Learning motor primitives and training a machine learning system using a linear-feedback-stabilized policy
US11714996B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 25, 2022 |
| Grant date | Aug 1, 2023 |
| Priority date | — |
| Expiry date | Jul 25, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer-implemented method of training a student machine learning system comprises receiving data indicating execution of an expert, determining one or more actions performed by the expert during the execution and a corresponding state-action Jacobian, and training the student machine learning system using a linear-feedback-stabilized policy. The linear-feedback-stabilized policy may be based on the state-action Jacobian. Also a neural network system for representing a space of probabilistic motor primitives, implemented by one or more computers. The neural network system comprises an encoder configured to generate latent variables based on a plurality of inputs, each input comprising a plurality of frames, and a decoder configured to generate an action based on one or more of the latent variables and a state.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.