Training neural networks using a prioritized experience memory
US10282662B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 11, 2018 |
| Grant date | May 7, 2019 |
| Priority date | — |
| Expiry date | May 11, 2038 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY04S10/50
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network used to select actions performed by a reinforcement learning agent interacting with an environment. In one aspect, a method includes maintaining a replay memory, where the replay memory stores pieces of experience data generated as a result of the reinforcement learning agent interacting with the environment. Each piece of experience data is associated with a respective expected learning progress measure that is a measure of an expected amount of progress made in the training of the neural network if the neural network is trained on the piece of experience data. The method further includes selecting a piece of experience data from the replay memory by prioritizing for selection pieces of experience data having relatively higher expected learning progress measures and training the neural network on the selected piece of experience data.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.