Action selection using interaction history graphs
US11636347B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 22, 2020 |
| Grant date | Apr 25, 2023 |
| Priority date | — |
| Expiry date | Jun 16, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/048
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a method comprises: obtaining a graph of nodes and edges that represents an interaction history of the agent with the environment; generating an encoded representation of the graph representing the interaction history of the agent with the environment; processing an input based on the encoded representation of the graph using an action selection neural network, in accordance with current values of action selection neural network parameters, to generate an action selection output; and selecting an action from a plurality of possible actions to be performed by the agent using the action selection output generated by the action selection neural network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.