Training behavior of an agent
US11182698B2 · kind B2 · utility
1Cited by
0References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jul 10, 2019 |
| Grant date | Nov 23, 2021 |
| Priority date | — |
| Expiry date | Jan 30, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/008
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An apparatus is described for training a behavior of an agent in a physical or digital environment. The apparatus comprises a memory storing the location of at least one reward token in the environment. The location has been specified by a user. At least one processor executes the agent in the environment according to a behavior policy. The processor is configured to observe values of variables comprising: an observation of the agent, an action of the agent and any reward resulting from the reward token. The processor is configured to update the behavior policy using reinforcement learning according to the observed values.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.