Controlling agents over long time scales using temporal value transport
US10789511B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 14, 2019 |
| Grant date | Sep 29, 2020 |
| Priority date | — |
| Expiry date | Oct 14, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network system used to control an agent interacting with an environment to perform a specified task. One of the methods includes causing the agent to perform a task episode in which the agent attempts to perform the specified task; for each of one or more particular time steps in the sequence: generating a modified reward for the particular time step from (i) the actual reward at the time step and (ii) value predictions at one or more time steps that are more than a threshold number of time steps after the particular time step in the sequence; and training, through reinforcement learning, the neural network system using at least the modified rewards for the particular time steps.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.