Neural network for reinforcement learning
US9349092B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 2, 2014 |
| Grant date | May 24, 2016 |
| Priority date | — |
| Expiry date | Jun 2, 2034 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A neural model for reinforcement-learning and for action-selection includes a plurality of channels, a population of input neurons in each of the channels, a population of output neurons in each of the channels, each population of input neurons in each of the channels coupled to each population of output neurons in each of the channels, and a population of reward neurons in each of the channels. Each channel of a population of reward neurons receives input from an environmental input, and is coupled only to output neurons in a channel that the reward neuron is part of. If the environmental input for a channel is positive, the corresponding channel of a population of output neurons are rewarded and have their responses reinforced, otherwise the corresponding channel of a population of output neurons are punished and have their responses attenuated.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.