Training action selection neural networks using a differentiable credit function
US11651208B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 22, 2018 |
| Grant date | May 16, 2023 |
| Priority date | — |
| Expiry date | Dec 28, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/092
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. A reinforcement learning neural network selects actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The reinforcement learning neural network has at least one input to receive an input observation characterizing a state of the environment and at least one output for determining an action to be performed by the agent in response to the input observation. The system includes a reward function network coupled to the reinforcement learning neural network. The reward function network has an input to receive reward data characterizing a reward provided by one or more states of the environment and is configured to determine a reward function to provide one or more target values for training the reinforcement learning neural network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.