Training action-selection neural networks from demonstrations using multiple losses
US12008077B1 · kind B1 · utility
0Cited by
6References
20Claims
0Family size
Assignee
Inventor
Key dates
| Filing date | Mar 13, 2023 |
| Grant date | Jun 11, 2024 |
| Priority date | — |
| Expiry date | Mar 13, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method of training an action selection neural network to perform a demonstrated task using a supervised learning technique. The action selection neural network is configured to receive demonstration data comprising actions to perform the task and rewards received for performing the actions. The action selection neural network has auxiliary prediction task neural networks on one or more of its intermediate outputs. The action selection policy neural network is trained using multiple combined losses, concurrently with the auxiliary prediction task neural networks.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.