Reinforcement learning using a relational network for generating data encoding relationships between entities in an environment
US11580429B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 20, 2019 |
| Grant date | Feb 14, 2023 |
| Priority date | — |
| Expiry date | May 20, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N7/01
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A neural network system is proposed, including an input network for extracting, from state data, respective entity data for each a plurality of entities which are present, or at least potentially present, in the environment. The entity data describes the entity. The neural network contains a relational network for parsing this data, which includes one or more attention blocks which may be stacked to perform successive actions on the entity data. The attention blocks each include a respective transform network for each of the entities. The transform network for each entity is able to transform data which the transform network receives for the entity into modified entity data for the entity, based on data for a plurality of the other entities. An output network is arranged to receive data output by the relational network, and use the received data to select a respective action.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.