Deep reinforcement learning based models for hard-exploration problems
US11829870B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 26, 2019 |
| Grant date | Nov 28, 2023 |
| Priority date | — |
| Expiry date | Apr 30, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG05B13/027
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A self-driving vehicle implements a deep reinforcement learning based model. The self-driving vehicle comprise one or more sensors configured to capture sensor data of an environment of the self-driving vehicle, a control system configured to navigate the self-driving vehicle, and a controller to determine and provide instructions to the control system. The controller implements a deep reinforcement learning based model that inputs the sensor data captured by the sensors to determine actions to perform by the control system. The model includes an archive storing states reachable by an agent in a training environment, each state stored in the archive is associated with a trajectory for reaching the state. The archive is generated by visiting states stored in the archive and performing actions to explore and find new states. New states are stored in the archive with their trajectories.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.